© 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. 2-RES-JB
    11. 8364
    Prev
    Next
    INDEX
    Explanations

    names or mentions of people and organizations, particularly related to politics and historical events

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the abbreviation "hr"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.72
     Totem
    -0.69
    BALL
    -0.69
    cens
    -0.67
     Point
    -0.62
    eties
    -0.62
     seeded
    -0.61
     Hots
    -0.60
     Austral
    -0.60
     Clash
    -0.59
    POSITIVE LOGITS
    ud
    0.98
    anging
    0.98
    uty
    0.97
    acht
    0.94
    iller
    0.93
    anged
    0.93
    hr
    0.90
    rr
    0.87
    yth
    0.87
    acket
    0.86
    Activations Density 0.005%

    No Known Activations