© 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 Local
    9. 6-RES_SCL-AJT
    11. 4162
    Prev
    Next
    INDEX
    Explanations

    information related to people's family background, specifically focusing on their parents and siblings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    +0.14
    0.6%
    420
    +0.14
    0.6%
    393
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.14
    0.32
    640
    +0.14
    0.26
    385
    +0.13
    0.18
    Negative Logits
    nels
    -0.87
    upid
    -0.84
    aceous
    -0.82
    uden
    -0.80
    etsk
    -0.78
    wcs
    -0.75
    motion
    -0.75
    phabet
    -0.74
    ickr
    -0.74
    £ı
    -0.74
    POSITIVE LOGITS
     slain
    0.80
     deceased
    0.79
     former
    0.79
     hers
    0.77
     Cul
    0.76
     Lank
    0.75
     Haz
    0.75
     Pam
    0.75
     Chev
    0.74
     Dat
    0.74
    Activations Density 12.872%

    No Known Activations