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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11740
    Prev
    Next
    INDEX
    Explanations

    phrases related to deep exploration, investigation, or analysis

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to exploration and analysis of depth or complexity

    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
    move
    -0.71
    kees
    -0.67
    oppable
    -0.66
    iannopoulos
    -0.66
    apest
    -0.64
    click
    -0.63
    Frames
    -0.61
    winner
    -0.59
    rily
    -0.59
    voice
    -0.59
    POSITIVE LOGITS
     trenches
    1.20
     depths
    1.19
     deeper
    1.10
     pockets
    1.09
     recess
    1.03
     deepest
    0.97
     depth
    0.95
     deep
    0.92
     darkest
    0.91
     roots
    0.91
    Activations Density 0.273%

    No Known Activations