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. 13292
    Prev
    Next
    INDEX
    Explanations

    phrases related to the degree or extent of something

    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
    +0.14
    0.8%
    762
    +0.09
    0.5%
    381
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.14
    0.30
    375
    +0.09
    0.07
    283
    +0.08
    0.02
    Negative Logits
    tty
    -0.62
    reth
    -0.60
    sbm
    -0.54
     Shuttle
    -0.53
     Tray
    -0.53
    tin
    -0.52
    imen
    -0.52
    itone
    -0.50
    brook
    -0.49
    RAW
    -0.49
    POSITIVE LOGITS
     extent
    0.60
     approximation
    0.59
    esm
    0.57
    olit
    0.54
    mma
    0.51
    forth
    0.50
     inacc
    0.50
     restitution
    0.49
    Æ
    0.48
     latitude
    0.48
    Activations Density 12.550%

    No Known Activations