© 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. 10-RES-JB
    11. 12825
    Prev
    Next
    INDEX
    Explanations

    words related to medical treatment or procedures

    oai_token-act-pair · gpt-3.5-turbo

    the end of the document or a clear document termination signal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Aren
    -0.63
    AUD
    -0.56
    Events
    -0.54
    external
    -0.54
    sheets
    -0.54
    weights
    -0.54
    eworks
    -0.54
    Att
    -0.53
    enges
    -0.53
    Iss
    -0.53
    POSITIVE LOGITS
    venge
    0.70
     lot
    0.69
    uras
    0.69
    usterity
    0.64
    sexual
    0.63
     poem
    0.63
     plurality
    0.62
     bunch
    0.62
     humanoid
    0.61
     nutshell
    0.61
    Activations Density 0.401%

    No Known Activations