© 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. 15295
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning specific political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or entities, particularly those that are significant figures or organizations

    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
    UAL
    -0.78
    ewski
    -0.73
     Gork
    -0.69
    ateurs
    -0.68
    nings
    -0.68
    sing
    -0.68
    rament
    -0.67
    noon
    -0.66
    Required
    -0.64
    IBLE
    -0.64
    POSITIVE LOGITS
     Haram
    1.04
    oro
    1.00
    vernment
    0.97
    NetMessage
    0.90
    oko
    0.88
    lé
    0.87
    annis
    0.83
    issan
    0.76
    wana
    0.75
    heastern
    0.74
    Activations Density 0.017%

    No Known Activations