© 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. 0-RES-JB
    11. 1162
    Prev
    Next
    INDEX
    Explanations

    political party affiliations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific political party or leader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scully
    -0.66
     saint
    -0.65
     tackling
    -0.65
    leans
    -0.64
    charg
    -0.63
    eways
    -0.61
    culosis
    -0.60
     Skinner
    -0.60
     lockdown
    -0.60
     bottleneck
    -0.60
    POSITIVE LOGITS
    JP
    3.98
    jp
    1.67
     Miz
    1.38
     JPEG
    1.12
    USD
    1.09
    ASC
    0.96
    MK
    0.95
    Israeli
    0.92
    ENG
    0.87
    RAW
    0.86
    Activations Density 0.016%

    No Known Activations