Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 33185
    Prev
    Next
    INDEX
    Explanations

    information related to specific events or situations that occur during a specified time period, particularly focusing on sports games or military operations

    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
    288
    +0.10
    0.6%
    447
    +0.10
    0.6%
    582
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.10
    0.14
    288
    +0.10
    0.24
    23
    +0.08
    0.12
    Negative Logits
    yip
    -0.60
    doms
    -0.59
    uron
    -0.56
    kson
    -0.53
    urat
    -0.51
    ourke
    -0.49
    ozy
    -0.48
    eus
    -0.48
    edom
    -0.47
    ault
    -0.47
    POSITIVE LOGITS
    ftime
    0.62
     halftime
    0.56
    istas
    0.50
    iday
    0.49
     Tanz
    0.48
    noon
    0.47
     Lamar
    0.47
    gression
    0.47
    FACE
    0.46
    retch
    0.46
    Activations Density 10.225%

    No Known Activations