© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 33303
    Prev
    Next
    INDEX
    Explanations

    text characters in a specific format, potentially related to details about an individual, democratic processes, or gaming instructions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.16
    0.8%
    115
    +0.11
    0.5%
    368
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.36
    193
    +0.11
    0.12
    618
    +0.09
    0.19
    Negative Logits
     è£ıè
    -0.56
     intersection
    -0.56
     subjective
    -0.52
     contradiction
    -0.51
     exec
    -0.51
     advoc
    -0.50
     defect
    -0.50
     nons
    -0.49
    DVD
    -0.49
     Hemp
    -0.48
    POSITIVE LOGITS
    TPPStreamerBot
    0.74
    edu
    0.70
    esi
    0.69
    vous
    0.67
    ensis
    0.65
    vt
    0.65
    hai
    0.63
    oÄŁ
    0.62
    lite
    0.62
    ji
    0.62
    Activations Density 30.298%

    No Known Activations