© 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. 33650
    Prev
    Next
    INDEX
    Explanations

    DDR3L memory specifications

    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
    311
    +0.10
    0.5%
    651
    +0.10
    0.5%
    696
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.24
    288
    +0.10
    0.24
    651
    +0.09
    0.13
    Negative Logits
    bes
    -0.71
    bub
    -0.69
    hall
    -0.68
    flies
    -0.68
    gdala
    -0.68
    ochet
    -0.66
    OGR
    -0.64
     Samar
    -0.64
    ths
    -0.64
    natureconservancy
    -0.64
    POSITIVE LOGITS
    ®
    0.71
    ĵĺ
    0.69
    iesel
    0.66
     DDR
    0.64
     maximum
    0.63
     ®
    0.62
    §
    0.61
    âĦ¢
    0.60
    Ģ
    0.59
     lanes
    0.58
    Activations Density 8.981%

    No Known Activations