© 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. 18339
    Prev
    Next
    INDEX
    Explanations

    names related to a specific person, potentially related to politics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names or terms associated with a particular individual or topic

    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
    acious
    -0.75
    ieth
    -0.73
    older
    -0.73
    iverse
    -0.71
     opio
    -0.67
    ividual
    -0.65
    reys
    -0.65
    ivity
    -0.65
    orescent
    -0.64
    ishable
    -0.64
    POSITIVE LOGITS
    arro
    0.90
     Rally
    0.85
    arak
    0.83
     Races
    0.72
    xon
    0.71
    ansas
    0.70
    BuyableInstoreAndOnline
    0.69
     Mane
    0.68
    BALL
    0.66
    agna
    0.65
    Activations Density 0.018%

    No Known Activations