© 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. 3-RES-JB
    11. 13552
    Prev
    Next
    INDEX
    Explanations

    mentions of chart positions on music charts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to music charts and film industry metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flask
    -0.65
    !--
    -0.62
    onomous
    -0.62
     Cato
    -0.62
     Alm
    -0.61
     attackers
    -0.61
    existent
    -0.60
    protein
    -0.59
     Mesh
    -0.59
     poor
    -0.59
    POSITIVE LOGITS
     premie
    0.93
     sitcom
    0.93
     airs
    0.92
     performer
    0.91
    DVD
    0.91
     viewership
    0.89
     actress
    0.88
     premiered
    0.87
     broadcaster
    0.85
    76561
    0.84
    Activations Density 0.294%

    No Known Activations