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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40003
    Prev
    Next
    INDEX
    Explanations

    activity-related terms and measurements, such as movement rate, achievements, challenges, and 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
    447
    +0.36
    1.6%
    288
    +0.16
    0.7%
    71
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.36
    0.11
    679
    +0.16
    0.17
    271
    +0.14
    0.07
    Negative Logits
    uran
    -0.84
    Boss
    -0.80
     passage
    -0.80
    gling
    -0.78
    ocard
    -0.75
    oiler
    -0.73
    ophe
    -0.72
    agar
    -0.69
    pper
    -0.68
    haul
    -0.67
    POSITIVE LOGITS
    ional
    1.07
    ivism
    0.94
     activity
    0.93
     activities
    0.91
    iveness
    0.86
    uality
    0.86
    ual
    0.86
     Activity
    0.85
    ivity
    0.84
    nesota
    0.80
    Activations Density 7.203%

    No Known Activations