© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3740
    Prev
    Next
    INDEX
    Explanations

    information related to air traffic, aviation, and traffic control systems

    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
    558
    +0.03
    0.5%
    179
    +0.03
    0.5%
    216
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    89
    +0.03
    0.02
    288
    +0.03
    0.03
    115
    +0.03
    0.02
    Negative Logits
    forth
    -0.21
    "],"
    -0.21
    back
    -0.19
    skip
    -0.19
    gradation
    -0.18
    hill
    -0.18
    adj
    -0.18
    ottest
    -0.18
    utive
    -0.18
    hard
    -0.18
    POSITIVE LOGITS
     mosqu
    0.23
    ongyang
    0.20
    anooga
    0.20
     umb
    0.20
     NAS
    0.19
    ographed
    0.19
     controllers
    0.19
     SERVICE
    0.19
     Profession
    0.18
    unta
    0.18
    Activations Density 0.101%

    No Known Activations