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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4436
    Prev
    Next
    INDEX
    Explanations

    phrases related to research findings or data analysis

    oai_token-act-pair · gpt-3.5-turbo

    references to research findings or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gger
    -0.72
    queue
    -0.67
    [_
    -0.63
    timer
    -0.63
    ifle
    -0.63
     besides
    -0.61
    erson
    -0.60
    icker
    -0.59
     forbid
    -0.59
    let
    -0.58
    POSITIVE LOGITS
     findings
    3.46
     conclusions
    1.99
     discoveries
    1.91
     results
    1.78
     observations
    1.66
     recommendations
    1.60
    results
    1.52
     insights
    1.44
     hypotheses
    1.42
     analyses
    1.42
    Activations Density 0.010%

    No Known Activations