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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 699
    Prev
    Next
    INDEX
    Explanations

    categories or classification terms

    oai_token-act-pair · gpt-3.5-turbo

    references to categories or classifications

    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
    zos
    -0.68
    OUGH
    -0.66
    arbon
    -0.65
    ONEY
    -0.65
    anoia
    -0.64
    rets
    -0.63
    arie
    -0.62
     anew
    -0.62
     reconnect
    -0.61
    ourn
    -0.60
    POSITIVE LOGITS
     category
    3.68
     categories
    2.62
    category
    2.39
     Category
    2.39
    Category
    2.02
     Categories
    1.84
     classification
    1.67
     genre
    1.45
     categor
    1.40
    ategory
    1.36
    Activations Density 0.012%

    No Known Activations