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. 45133
    Prev
    Next
    INDEX
    Explanations

    terms related to neuroinflammation and its impact on memory and behavior

    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
    699
    +0.14
    0.6%
    649
    +0.13
    0.5%
    182
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.14
    0.02
    711
    +0.13
    0.03
    288
    +0.11
    0.17
    Negative Logits
    EEK
    -0.93
    ĸļ
    -0.89
    rir
    -0.89
    ivities
    -0.82
    ãĥ¯ãĥ³
    -0.81
    urai
    -0.80
    CHA
    -0.79
    herer
    -0.77
    URA
    -0.77
    herty
    -0.76
    POSITIVE LOGITS
    ysis
    1.35
    ity
    1.26
    ogue
    1.07
    ities
    1.00
    arial
    0.94
    ogy
    0.91
    acies
    0.91
    ized
    0.88
    ization
    0.86
     piety
    0.83
    Activations Density 6.676%

    No Known Activations