© 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. 35240
    Prev
    Next
    INDEX
    Explanations

    dates or historical events, particularly in relation to literature, politics, and sports

    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
    +0.24
    1.6%
    662
    +0.06
    0.4%
    134
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.24
    0.23
    393
    +0.06
    0.33
    382
    +0.06
    0.11
    Negative Logits
     (@
    -0.52
     drip
    -0.45
     -->
    -0.45
    )</
    -0.43
     ripple
    -0.43
     hugs
    -0.43
     answ
    -0.41
    .</
    -0.40
     {*
    -0.40
    hub
    -0.38
    POSITIVE LOGITS
    ibliography
    0.64
    odore
    0.64
    wards
    0.61
    tymology
    0.61
    senal
    0.54
    ascus
    0.53
    chieve
    0.52
    ometime
    0.52
    anmar
    0.50
    cyclopedia
    0.50
    Activations Density 17.381%

    No Known Activations