© 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5777
    Prev
    Next
    INDEX
    Explanations

    prices of products and deals

    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
    245
    +0.15
    0.5%
    162
    +0.15
    0.5%
    165
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    165
    +0.15
    0.05
    495
    +0.15
    0.06
    162
    +0.14
    0.05
    Negative Logits
    ãĤ¡
    -1.06
    ificant
    -0.98
    ampa
    -0.95
    ordon
    -0.95
    oken
    -0.94
     Starr
    -0.94
     Nightmares
    -0.94
    hing
    -0.93
    GGGGGGGG
    -0.93
    umbn
    -0.91
    POSITIVE LOGITS
    -$
    1.47
    /$
    1.24
     USD
    1.23
     cents
    1.22
     postage
    1.17
     upfront
    1.16
    AUD
    1.14
    billion
    1.09
     per
    1.09
     installments
    1.06
    Activations Density 0.731%

    No Known Activations