© 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. 10272
    Prev
    Next
    INDEX
    Explanations

    references to self-driving or autonomous technology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of self-driving technology

    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
     GOODMAN
    -0.76
     Syndicate
    -0.75
     Ashe
    -0.74
     Orchestra
    -0.74
     XIII
    -0.73
    ropolitan
    -0.69
     Flavoring
    -0.69
    ————————
    -0.67
    ĸļ
    -0.67
    ī
    -0.66
    POSITIVE LOGITS
    destruct
    1.26
     destruct
    1.09
    upload
    0.86
     explanatory
    0.84
    lect
    0.81
    same
    0.77
    uls
    0.77
    conscious
    0.77
    ortium
    0.76
    uded
    0.75
    Activations Density 0.015%

    No Known Activations