© 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. 7594
    Prev
    Next
    INDEX
    Explanations

    references to a specific music television program

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Rocky" and related terms associated with it, particularly in the context of music and culture

    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
    ascript
    -1.02
    iqueness
    -0.71
    quickShipAvailable
    -0.71
    owship
    -0.69
    Newsletter
    -0.68
    URA
    -0.67
     deceive
    -0.66
    ICLE
    -0.65
    channelAvailability
    -0.64
    blance
    -0.64
    POSITIVE LOGITS
    Mania
    0.67
    anski
    0.65
     Gibraltar
    0.64
     footh
    0.64
    Thumbnail
    0.64
     scissors
    0.63
    adesh
    0.62
    iland
    0.62
     Archdemon
    0.61
     docks
    0.61
    Activations Density 0.169%

    No Known Activations