© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 256
    Prev
    Next
    INDEX
    Explanations

    specific sections or categories within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "section" and its variations

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

    No Comments

    Negative Logits
    cia
    -0.79
    Iv
    -0.77
     opio
    -0.70
    Grand
    -0.68
    ILLE
    -0.67
     monetary
    -0.63
    cffff
    -0.62
     gripping
    -0.60
    claimed
    -0.60
    ce
    -0.60
    POSITIVE LOGITS
     sections
    0.84
    lation
    0.82
    witz
    0.79
    enium
    0.79
    crew
    0.74
    section
    0.73
    owell
    0.73
    bars
    0.70
    edin
    0.70
    isions
    0.70
    Activations Density 0.010%

    No Known Activations