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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 4301
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interaction and communication

    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
    +0.22
    1.2%
    195
    +0.13
    0.7%
    679
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.22
    0.13
    271
    +0.13
    0.05
    263
    +0.12
    0.07
    Negative Logits
    cott
    -0.64
    zn
    -0.62
    peria
    -0.62
    aft
    -0.59
    prus
    -0.57
    ciples
    -0.56
    haps
    -0.56
    zik
    -0.55
    fork
    -0.54
    GE
    -0.54
    POSITIVE LOGITS
     interactions
    0.81
    ivity
    0.79
    ually
    0.79
    ively
    0.74
     interaction
    0.73
    uate
    0.73
    iences
    0.72
    ioned
    0.67
    uality
    0.65
    ivating
    0.65
    Activations Density 7.778%

    No Known Activations