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. 2-RES-JB
    6. 9824
    Prev
    Next
    INDEX
    Explanations

    suggestions or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    references to suggestions or advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipel
    -0.76
    otypes
    -0.75
    otype
    -0.72
    ccording
    -0.71
    mberg
    -0.69
    nces
    -0.68
    dig
    -0.68
    tu
    -0.67
    IGH
    -0.67
    arton
    -0.65
    POSITIVE LOGITS
     suggestions
    1.06
     suggestion
    1.03
     hint
    0.90
     hints
    0.90
     Suggest
    0.86
    uggest
    0.82
    suggest
    0.82
    IONS
    0.77
     suggested
    0.72
     sugg
    0.72
    Activations Density 0.018%

    No Known Activations