© 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. 2-RES-JB
    11. 1052
    Prev
    Next
    INDEX
    Explanations

    references to high points or peaks

    oai_token-act-pair · gpt-3.5-turbo

    references to levels or maxima of various metrics or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oured
    -0.74
    signed
    -0.70
     transpl
    -0.69
    cheat
    -0.67
    harm
    -0.66
    icate
    -0.66
    erie
    -0.66
    onsense
    -0.65
    icator
    -0.65
    YA
    -0.64
    POSITIVE LOGITS
     peaks
    0.85
     peak
    0.82
     heights
    0.80
     height
    0.78
     highs
    0.77
     erection
    0.76
     lows
    0.72
     earners
    0.71
    phrine
    0.70
     pinnacle
    0.68
    Activations Density 0.007%

    No Known Activations