© 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. 2611
    Prev
    Next
    INDEX
    Explanations

    phrases related to valuable or important information, often being a key point or insight

    oai_token-act-pair · gpt-3.5-turbo

    references to 'tips' that suggest deeper underlying issues or themes

    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
    ively
    -0.77
    venants
    -0.71
    lishes
    -0.68
     BRA
    -0.67
     Zed
    -0.64
     Springer
    -0.63
    effic
    -0.63
    ufact
    -0.62
     Bom
    -0.61
     Mov
    -0.61
    POSITIVE LOGITS
     jar
    1.21
    ster
    1.14
    sters
    1.10
     tip
    1.03
    sy
    1.02
     iceberg
    1.01
     toes
    1.01
    toe
    0.97
    tip
    0.96
    off
    0.92
    Activations Density 0.048%

    No Known Activations