Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 733
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal identity and introspection

    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
    447
    +0.18
    0.7%
    580
    +0.13
    0.5%
    719
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.26
    640
    +0.13
    0.24
    739
    +0.12
    0.07
    Negative Logits
    ierrez
    -0.93
     CoC
    -0.90
    ixel
    -0.90
     conflic
    -0.89
    entially
    -0.89
    untled
    -0.86
    ilater
    -0.84
    ationally
    -0.84
     volunte
    -0.84
    eatures
    -0.83
    POSITIVE LOGITS
     Thou
    1.15
     thou
    1.11
    tis
    1.10
     Caesar
    1.09
     mighty
    1.08
     Judah
    1.08
     Blessed
    1.07
     thee
    1.06
     whence
    1.04
     thy
    1.02
    Activations Density 8.809%

    No Known Activations