© 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. 1-RES-JB
    11. 3235
    Prev
    Next
    INDEX
    Explanations

    the word "is" within sentences

    oai_token-act-pair · gpt-3.5-turbo

    statements about likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.85
     sidx
    -0.80
    wig
    -0.77
    Subject
    -0.74
    blind
    -0.73
    reen
    -0.73
    ware
    -0.69
    iciary
    -0.67
    HUD
    -0.65
     Instruments
    -0.64
    POSITIVE LOGITS
    Ĭ±
    0.69
    ĻĤ
    0.69
     Extra
    0.68
     livest
    0.67
    ģĸ
    0.67
    ģ«
    0.65
    gon
    0.63
    ĺ
    0.63
    rolet
    0.62
    ĺħ
    0.62
    Activations Density 0.000%

    No Known Activations