© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6747
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, specifically mentioning the term "Mother" followed by a number or other associated words

    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
    238
    +0.17
    0.6%
    377
    +0.15
    0.5%
    372
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.17
    0.08
    372
    +0.15
    0.06
    711
    +0.12
    0.05
    Negative Logits
     Flavoring
    -1.28
    NRS
    -1.06
    EY
    -0.97
    OPLE
    -0.93
    ickr
    -0.92
    vernment
    -0.92
    okers
    -0.90
    ratulations
    -0.88
    kefeller
    -0.87
    ype
    -0.87
    POSITIVE LOGITS
    hood
    1.49
    ship
    1.36
    hesis
    1.32
    heses
    1.27
    hetically
    1.23
    stones
    1.19
    hetical
    1.17
    load
    1.15
    boards
    1.13
    plate
    1.07
    Activations Density 1.592%

    No Known Activations