© 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. 5326
    Prev
    Next
    INDEX
    Explanations

    phrases related to caves

    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
    313
    +0.11
    0.5%
    70
    +0.10
    0.5%
    461
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.07
    288
    +0.10
    0.07
    99
    +0.10
    0.05
    Negative Logits
    abeth
    -0.80
    ually
    -0.79
    abad
    -0.79
    ion
    -0.73
    ivity
    -0.73
    ovation
    -0.70
    imated
    -0.69
    bsp
    -0.68
    iets
    -0.68
    chrom
    -0.67
    POSITIVE LOGITS
    llan
    1.00
    tta
    0.96
    astern
    0.81
    ll
    0.79
    ocene
    0.77
    erness
    0.76
    rers
    0.76
    liest
    0.75
    croft
    0.75
    resses
    0.74
    Activations Density 0.802%

    No Known Activations