© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1183
    Prev
    Next
    INDEX
    Explanations

    words related to giving credit or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    347
    +0.10
    0.5%
    11
    +0.10
    0.5%
    329
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.10
    0.01
    661
    +0.10
    0.02
    551
    +0.09
    0.02
    Negative Logits
    SPONSORED
    -0.81
    fab
    -0.74
    çİĭ
    -0.71
    STON
    -0.67
    ichick
    -0.66
     Osw
    -0.65
    ews
    -0.65
    ools
    -0.65
    dose
    -0.63
    HF
    -0.63
    POSITIVE LOGITS
     representation
    0.62
     accuracy
    0.60
     equal
    0.60
     comparable
    0.60
     Dying
    0.57
     strictly
    0.57
     understatement
    0.56
     outnumbered
    0.56
     reviewer
    0.56
     bra
    0.55
    Activations Density 0.106%

    No Known Activations