© 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. 3893
    Prev
    Next
    INDEX
    Explanations

    information about locations and quantities

    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
    +0.18
    0.7%
    241
    +0.12
    0.5%
    679
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.19
    575
    +0.12
    0.17
    258
    +0.10
    0.15
    Negative Logits
    ebin
    -0.80
    Leader
    -0.75
    esi
    -0.67
     Tire
    -0.65
     Territories
    -0.64
     Fury
    -0.64
     Differences
    -0.64
     Leader
    -0.64
     Clause
    -0.63
    adle
    -0.63
    POSITIVE LOGITS
     including
    1.16
     ranging
    1.10
     totaling
    1.09
     imaginable
    1.03
    paces
    1.00
    mith
    1.00
    hips
    0.96
     converge
    0.96
    poons
    0.96
     spanning
    0.95
    Activations Density 3.823%

    No Known Activations