© 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. 40058
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific concept or action occurring once

    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
    706
    +0.16
    0.6%
    408
    +0.14
    0.5%
    99
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    706
    +0.16
    0.10
    471
    +0.14
    0.07
    162
    +0.12
    0.06
    Negative Logits
    Í
    -0.90
    RIC
    -0.88
    onga
    -0.85
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.84
    roth
    -0.83
    urga
    -0.82
    alf
    -0.82
    rug
    -0.81
    iery
    -0.80
    çĶ°
    -0.80
    POSITIVE LOGITS
    soever
    0.95
     again
    0.92
     bitten
    0.92
     Upon
    0.89
    falls
    0.84
     upon
    0.78
     mastered
    0.78
     glimps
    0.77
     jour
    0.77
    handedly
    0.76
    Activations Density 3.491%

    No Known Activations