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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 44884
    Prev
    Next
    INDEX
    Explanations

    information related to ice or icy conditions

    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
    +0.20
    1.0%
    420
    +0.12
    0.6%
    442
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.20
    0.07
    683
    +0.12
    0.06
    271
    +0.12
    0.03
    Negative Logits
    hovah
    -0.72
    ajo
    -0.70
    yrinth
    -0.68
    lisher
    -0.68
    asca
    -0.67
    icals
    -0.65
    risk
    -0.65
    rompt
    -0.65
    arov
    -0.64
    onite
    -0.64
    POSITIVE LOGITS
    lli
    1.19
    lla
    1.08
    llular
    1.03
    llo
    0.98
    llan
    0.95
    xp
    0.91
    ptive
    0.84
    ll
    0.83
    ptives
    0.80
    cream
    0.78
    Activations Density 10.874%

    No Known Activations