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. 13335
    Prev
    Next
    INDEX
    Explanations

    phrases related to team support and camaraderie in a sports 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
    447
    +0.11
    0.8%
    728
    +0.07
    0.5%
    38
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.44
    6
    +0.07
    0.25
    64
    +0.07
    -0.25
    Negative Logits
    \":
    -0.49
     charms
    -0.49
     augment
    -0.46
    azes
    -0.45
    tein
    -0.42
     foreseeable
    -0.42
    TPPStreamerBot
    -0.40
     iceberg
    -0.40
    achus
    -0.39
    umbn
    -0.39
    POSITIVE LOGITS
    They
    0.55
     Continued
    0.54
    Weak
    0.51
    There
    0.50
    Develop
    0.50
    It
    0.50
    earchers
    0.49
    Commercial
    0.49
    Management
    0.49
    Different
    0.49
    Activations Density 13.188%

    No Known Activations