© 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
    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. 14378
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to computer programming and software development

    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
    195
    +0.21
    0.7%
    701
    +0.19
    0.6%
    739
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.21
    0.07
    701
    +0.19
    0.06
    284
    +0.18
    0.06
    Negative Logits
    ======
    -1.30
    mson
    -1.30
    kson
    -1.27
    ttle
    -1.16
    urity
    -1.12
    ãĤµ
    -1.09
    berus
    -1.07
    utic
    -1.06
    ifted
    -1.02
    HCR
    -1.01
    POSITIVE LOGITS
    ragon
    1.54
    ering
    1.37
    erer
    1.32
    orf
    1.30
     Rib
    1.23
    itional
    1.22
    ishly
    1.19
    rive
    1.19
    rawn
    1.18
    iverse
    1.17
    Activations Density 1.342%

    No Known Activations