© 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. 849
    Prev
    Next
    INDEX
    Explanations

    phrases related to author names and creative works

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial institutions and governance

    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
    bral
    -0.63
    iannopoulos
    -0.60
    POSE
    -0.60
    anmar
    -0.58
    ETHOD
    -0.53
    etermin
    -0.52
    letter
    -0.52
    hatt
    -0.52
    SEE
    -0.52
    Narr
    -0.51
    POSITIVE LOGITS
     by
    2.05
    by
    1.74
    By
    1.51
     By
    1.50
     BY
    1.46
    bys
    1.04
    BY
    0.95
    byter
    0.82
    Enlarge
    0.77
     aback
    0.74
    Activations Density 2.319%

    No Known Activations