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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13422
    Prev
    Next
    INDEX
    Explanations

    random actions or occurrences amidst a larger context

    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
    516
    +0.10
    0.5%
    569
    +0.10
    0.5%
    646
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.10
    0.10
    422
    +0.10
    0.07
    289
    +0.10
    0.01
    Negative Logits
    orem
    -0.74
    retty
    -0.70
    iens
    -0.68
    antics
    -0.67
    ador
    -0.64
    ilion
    -0.63
    osaurs
    -0.63
    ados
    -0.61
    heses
    -0.61
    arella
    -0.61
    POSITIVE LOGITS
     planted
    0.95
     allocated
    0.91
     configured
    0.91
     selected
    0.88
     distributed
    0.88
     sourced
    0.86
     spaced
    0.85
     dispersed
    0.85
     separated
    0.84
     populated
    0.84
    Activations Density 4.796%

    No Known Activations