© 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. 7038
    Prev
    Next
    INDEX
    Explanations

    numerical values in a specific format within a document

    oai_token-act-pair · gpt-3.5-turbo

    timestamps and date-related information

    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
    sson
    -0.75
    rome
    -0.63
    stood
    -0.61
     Grimoire
    -0.61
    Äĩ
    -0.61
    rik
    -0.58
    cum
    -0.57
    sed
    -0.57
    enne
    -0.57
    panic
    -0.56
    POSITIVE LOGITS
     SHARES
    1.07
    NEWS
    0.98
    News
    0.92
     Shares
    0.89
     PH
    0.84
     NEWS
    0.81
     Comments
    0.80
     Hours
    0.78
     Investig
    0.78
     IMAGES
    0.78
    Activations Density 0.073%

    No Known Activations