© 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. 7-RES-JB
    11. 21403
    Prev
    Next
    INDEX
    Explanations

    references to left-handedness

    oai_token-act-pair · gpt-3.5-turbo

    references to a person's handedness, specifically left-handed and right-handed characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anamo
    -0.96
    atis
    -0.94
    CHAT
    -0.90
    PsyNetMessage
    -0.86
    ublic
    -0.82
    idian
    -0.81
    actionDate
    -0.78
    advertising
    -0.78
    qqa
    -0.78
    burgh
    -0.77
    POSITIVE LOGITS
    ness
    1.05
     nodd
    0.79
     crane
    0.76
     barb
    0.75
     axe
    0.74
     cir
    0.73
     arrow
    0.72
     sword
    0.72
     tilt
    0.71
     elbows
    0.71
    Activations Density 0.043%

    No Known Activations