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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39490
    Prev
    Next
    INDEX
    Explanations

    information related to pregnancy and bacterial influences on health

    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
    746
    +0.03
    0.5%
    472
    +0.03
    0.5%
    421
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.03
    0.11
    149
    +0.03
    0.03
    479
    +0.03
    -0.01
    Negative Logits
    Tes
    -0.17
     req
    -0.15
    Contribut
    -0.15
     bis
    -0.14
    hammer
    -0.14
    UID
    -0.14
    Guide
    -0.14
    FG
    -0.14
     Kro
    -0.14
     totaling
    -0.14
    POSITIVE LOGITS
    esis
    0.23
    rals
    0.23
    iae
    0.22
    iated
    0.21
    rums
    0.20
    ral
    0.20
    cair
    0.18
    riel
    0.18
    iors
    0.18
    iak
    0.18
    Activations Density 20.648%

    No Known Activations