© 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. 11-RES-JB
    11. 3873
    Prev
    Next
    INDEX
    Explanations

    submissions with a specific format or keyword

    oai_token-act-pair · gpt-3.5-turbo

    references to submissions or contributions in a document

    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
     laughter
    -0.64
     fet
    -0.64
    FUL
    -0.62
    ATHER
    -0.60
     Hammer
    -0.60
     fingertips
    -0.59
     flared
    -0.58
     fingerprint
    -0.57
     Muse
    -0.57
     Emer
    -0.57
    POSITIVE LOGITS
    stantial
    1.61
    sequent
    1.59
    sequently
    1.57
    mitted
    1.53
    scription
    1.52
    stant
    1.41
    scrib
    1.39
    missions
    1.38
    marine
    1.38
    ordinate
    1.37
    Activations Density 0.021%

    No Known Activations