© 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. 14830
    Prev
    Next
    INDEX
    Explanations

    instances of legal or official language

    oai_token-act-pair · gpt-3.5-turbo

    instances of the articles 'an' and 'a', signaling noun phrases or specific references in the text

    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
     outweigh
    -0.76
     someday
    -0.71
    onto
    -0.68
     existed
    -0.68
     outwe
    -0.64
    itiz
    -0.63
     exists
    -0.60
    ourge
    -0.59
    ores
    -0.58
     depended
    -0.57
    POSITIVE LOGITS
     nutshell
    0.94
     meantime
    0.76
     vein
    0.74
     context
    0.73
     mode
    0.71
     largeDownload
    0.70
    initialized
    0.70
    opsis
    0.70
    idav
    0.69
    hent
    0.69
    Activations Density 0.250%

    No Known Activations