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. 13276
    Prev
    Next
    INDEX
    Explanations

    numbers and technical measurements

    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
    +0.21
    0.9%
    640
    +0.17
    0.7%
    160
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.21
    0.08
    393
    +0.17
    0.21
    640
    +0.17
    0.19
    Negative Logits
     Fletcher
    -0.81
     "'
    -0.80
     stalking
    -0.79
     Loki
    -0.76
     Ark
    -0.74
     swat
    -0.74
     ""
    -0.73
     Carlton
    -0.73
     disgu
    -0.72
     Arabian
    -0.72
    POSITIVE LOGITS
    etc
    1.27
    oct
    1.09
    1000
    1.05
    Flickr
    1.03
    trade
    1.02
    present
    1.00
    UV
    1.00
    PUT
    1.00
    single
    0.99
    usr
    0.97
    Activations Density 8.397%

    No Known Activations