© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13722
    Prev
    Next
    INDEX
    Explanations

    names of Hollywood figures and references to Hollywood industry scandals

    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
    288
    +0.19
    0.8%
    167
    +0.16
    0.6%
    527
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.05
    752
    +0.16
    0.04
    67
    +0.14
    0.04
    Negative Logits
    ktop
    -1.22
    arity
    -0.86
    terday
    -0.77
    imate
    -0.77
    pell
    -0.76
    İĭ
    -0.76
    rompt
    -0.75
    theless
    -0.75
    imates
    -0.75
     constitutionally
    -0.72
    POSITIVE LOGITS
     Reporter
    1.09
     studios
    1.00
     Studios
    0.97
     mog
    0.97
     Hills
    0.96
    stars
    0.96
     blockbuster
    0.91
     movies
    0.89
     productions
    0.89
     Pictures
    0.87
    Activations Density 0.331%

    No Known Activations