© 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. 3205
    Prev
    Next
    INDEX
    Explanations

    phrases describing legal or policy actions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal consequences

    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
    ERY
    -0.85
    CG
    -0.79
     VIDEOS
    -0.75
    Walker
    -0.73
    alus
    -0.72
    RM
    -0.71
    STAR
    -0.70
    loading
    -0.68
    NRS
    -0.67
    inar
    -0.67
    POSITIVE LOGITS
    nces
    0.73
     accus
    0.66
    itially
    0.65
     Pwr
    0.64
    gged
    0.63
    */(
    0.62
    umbn
    0.61
    phrine
    0.61
    anged
    0.61
    ationally
    0.61
    Activations Density 0.000%

    No Known Activations