© 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 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. 7170
    Prev
    Next
    INDEX
    Explanations

    actions related to providing help or support to others

    oai_token-act-pair · gpt-3.5-turbo
    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
    bang
    -0.66
    mini
    -0.63
    ndra
    -0.62
    ortex
    -0.62
    ppings
    -0.62
    ãĤ¦ãĤ¹
    -0.61
    attribute
    -0.61
    ãĥ¼ãĥ«
    -0.59
    nova
    -0.59
    iannopoulos
    -0.58
    POSITIVE LOGITS
     with
    0.74
     efforts
    0.71
     in
    0.68
     landowners
    0.65
     financially
    0.65
    umsy
    0.64
     technicians
    0.64
    ieth
    0.63
     us
    0.62
     digestion
    0.62
    Activations Density 0.101%

    No Known Activations