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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4201
    Prev
    Next
    INDEX
    Explanations

    words related to physical injuries and medical incidents

    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
    +0.18
    0.8%
    314
    +0.16
    0.7%
    640
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.18
    0.26
    160
    +0.16
    0.21
    314
    +0.16
    -0.00
    Negative Logits
    ulhu
    -0.90
     Richards
    -0.83
     Lanka
    -0.70
     Ell
    -0.69
     Claus
    -0.67
    esson
    -0.67
     Kern
    -0.66
     Borders
    -0.65
     Phi
    -0.65
    ãģ®éŃĶ
    -0.65
    POSITIVE LOGITS
    based
    1.22
    sized
    1.16
    operated
    1.15
    tested
    1.13
    saving
    1.12
    driven
    1.08
    to
    1.06
    themed
    1.06
    intensive
    1.03
    produced
    1.02
    Activations Density 9.255%

    No Known Activations