© 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. 1268
    Prev
    Next
    INDEX
    Explanations

    mentions of specific years or dates of birth, particularly when comparing two different individuals

    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
    414
    +0.18
    0.5%
    459
    +0.16
    0.5%
    365
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    716
    +0.18
    0.04
    201
    +0.16
    0.04
    545
    +0.16
    0.04
    Negative Logits
    phis
    -1.39
    awaru
    -1.22
    phasis
    -1.22
     tiss
    -1.21
    olicy
    -1.21
    intendent
    -1.19
    uko
    -1.15
     referen
    -1.15
    eredith
    -1.14
    ahime
    -1.14
    POSITIVE LOGITS
    lings
    1.35
    born
    1.09
    nings
    1.05
    stellar
    1.05
     Born
    1.04
    stein
    1.04
     abroad
    1.04
     pains
    1.01
    ness
    1.01
    holm
    1.00
    Activations Density 0.739%

    No Known Activations