© 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. 11-RES-JB
    11. 9877
    Prev
    Next
    INDEX
    Explanations

    statements related to political decisions being made or voted on

    oai_token-act-pair · gpt-3.5-turbo

    instances of legislative actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĨĴ
    -0.79
    anooga
    -0.73
    felt
    -0.69
    ĺħ
    -0.69
    ;;;;;;;;
    -0.69
     posing
    -0.63
    Lear
    -0.63
     lurking
    -0.63
     Trainer
    -0.62
    sle
    -0.61
    POSITIVE LOGITS
     expel
    1.43
     approve
    1.30
     legalize
    1.28
     postpone
    1.26
     revoke
    1.25
     suspend
    1.21
     terminate
    1.21
     exclude
    1.20
     authorize
    1.20
     oust
    1.18
    Activations Density 0.157%

    No Known Activations