© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 18449
    Prev
    Next
    INDEX
    Explanations

    questions or statements involving questioning about actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    questions about information and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tails
    -0.85
    \\\\\\\\
    -0.79
    astered
    -0.77
    esm
    -0.76
    uned
    -0.76
    arget
    -0.76
    alde
    -0.72
    rovers
    -0.72
    icked
    -0.69
    tra
    -0.69
    POSITIVE LOGITS
     Baz
    0.72
     pige
    0.71
     calib
    0.70
     forgiveness
    0.70
     anybody
    0.69
     permission
    0.66
     possible
    0.66
     anyone
    0.66
     bothered
    0.65
     exactly
    0.64
    Activations Density 0.085%

    No Known Activations