© 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. 18367
    Prev
    Next
    INDEX
    Explanations

    phrases related to political propositions or bills

    oai_token-act-pair · gpt-3.5-turbo

    references to specific propositions or ballot measures

    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
    soever
    -0.76
    esome
    -0.70
     Carib
    -0.66
    realDonaldTrump
    -0.64
    gel
    -0.64
    uckle
    -0.63
    Interstitial
    -0.63
     fingertips
    -0.63
     GOODMAN
    -0.62
    lla
    -0.59
    POSITIVE LOGITS
    aganda
    1.17
    onents
    1.17
    osition
    1.13
    onent
    1.08
    Prop
    1.05
    ulsion
    1.03
    osed
    0.97
    hetically
    0.92
    hetical
    0.91
     Proposition
    0.90
    Activations Density 0.009%

    No Known Activations