© 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. 0-RES-JB
    11. 1186
    Prev
    Next
    INDEX
    Explanations

    words related to speed or high velocity

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "super" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EDITION
    -0.76
    bound
    -0.71
    ocus
    -0.69
    eworld
    -0.68
     BLM
    -0.68
    RT
    -0.68
    ALK
    -0.67
    alde
    -0.67
    ģ«
    -0.66
     Canyon
    -0.66
    POSITIVE LOGITS
     su
    3.56
     Su
    1.56
    Su
    1.55
    su
    1.52
     suc
    1.38
     sus
    1.34
     SU
    1.29
     Sup
    1.23
    sup
    1.14
     sup
    1.13
    Activations Density 0.010%

    No Known Activations