© 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. 10032
    Prev
    Next
    INDEX
    Explanations

    information related to predominance or focus on a specific subject or topic

    oai_token-act-pair · gpt-3.5-turbo

    words that describe the primary focus or main aspects of a topic

    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
    anth
    -0.77
    orf
    -0.72
    emption
    -0.72
    hawk
    -0.70
    Express
    -0.70
    eon
    -0.70
    ENA
    -0.69
    each
    -0.67
    Ö¼
    -0.65
    uers
    -0.64
    POSITIVE LOGITS
     consisted
    0.92
     consisting
    0.91
     ceremonial
    0.89
     comprised
    0.86
     concerned
    0.83
     consists
    0.83
     focused
    0.82
     consist
    0.81
     cosmetic
    0.80
     composed
    0.76
    Activations Density 0.066%

    No Known Activations