© 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 EvalsExportsinterp-engineNEWAPI 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. 35582
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical condition and the state of objects or places

    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
    +0.20
    1.2%
    481
    +0.10
    0.6%
    638
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.20
    0.18
    724
    +0.10
    0.17
    35
    +0.07
    0.08
    Negative Logits
    enge
    -0.49
     blinded
    -0.46
     Regions
    -0.46
    udic
    -0.45
    =#
    -0.44
    allowed
    -0.44
     narrowed
    -0.43
     nominated
    -0.43
     approves
    -0.42
     shoulder
    -0.42
    POSITIVE LOGITS
     lately
    0.54
     Dragonbound
    0.53
    tenance
    0.51
     rebuilding
    0.50
    stadt
    0.50
    nered
    0.50
     thanks
    0.50
    smanship
    0.50
     proportions
    0.48
    deb
    0.45
    Activations Density 9.780%

    No Known Activations