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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 45339
    Prev
    Next
    INDEX
    Explanations

    instances of sudden intrusions or interruptions

    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
    323
    +0.09
    0.5%
    547
    +0.09
    0.5%
    656
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.09
    0.29
    393
    +0.09
    0.30
    362
    +0.08
    0.14
    Negative Logits
     postponed
    -0.50
     conveyed
    -0.50
     priorit
    -0.49
     banished
    -0.49
    entimes
    -0.49
     timetable
    -0.48
    ennis
    -0.47
    ians
    -0.47
    issues
    -0.46
     learnt
    -0.46
    POSITIVE LOGITS
    pload
    0.61
    mson
    0.56
    taining
    0.55
    Ò
    0.54
    ews
    0.52
    ochet
    0.52
     adulthood
    0.50
    ydia
    0.49
    Wall
    0.48
    ital
    0.47
    Activations Density 12.562%

    No Known Activations