© 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. 8-RES-JB
    11. 16835
    Prev
    Next
    INDEX
    Explanations

    unusual characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ponies
    -0.65
     Tues
    -0.63
     seeds
    -0.62
     multiplication
    -0.62
     Pike
    -0.62
    etsk
    -0.61
     intersections
    -0.61
     override
    -0.60
     impulse
    -0.60
     kernels
    -0.60
    POSITIVE LOGITS
    ÃĽ
    1.02
    ï¸ı
    0.93
    gypt
    0.89
    ñ
    0.87
    ÃįÃį
    0.86
    lean
    0.85
    û
    0.83
    Ãł
    0.82
    hl
    0.82
    £
    0.81
    Activations Density 0.024%

    No Known Activations