© 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. 4-RES-JB
    11. 14811
    Prev
    Next
    INDEX
    Explanations

    studies and research-related phrases related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of studies or research findings

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

    No Comments

    Negative Logits
     retaliate
    -0.76
     accompl
    -0.72
     appe
    -0.70
     punishable
    -0.67
     grenades
    -0.66
    ĺħ
    -0.65
    çİĭ
    -0.64
     whatsoever
    -0.64
     overpowered
    -0.64
    Ń·
    -0.64
    POSITIVE LOGITS
     methodology
    1.01
     methodological
    0.99
     statistical
    0.96
     study
    0.95
     questionnaire
    0.92
     research
    0.90
     quantitative
    0.88
     researchers
    0.87
     analysed
    0.86
     survey
    0.86
    Activations Density 0.991%

    No Known Activations