© 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. 22639
    Prev
    Next
    INDEX
    Explanations

    numerical values related to prices or costs

    oai_token-act-pair · gpt-3.5-turbo

    references to pricing and monetary values

    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
    20439
    -0.83
    ullivan
    -0.80
    regon
    -0.80
    rity
    -0.79
    alf
    -0.79
    etheless
    -0.78
    algia
    -0.76
    eworks
    -0.75
    eln
    -0.74
    aug
    -0.73
    POSITIVE LOGITS
     tag
    1.40
     gou
    1.21
     tags
    1.19
    uming
    0.98
     hike
    0.96
    payer
    0.95
     differential
    0.93
    tag
    0.90
     hikes
    0.88
     quotation
    0.86
    Activations Density 0.062%

    No Known Activations