© 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. 16355
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the potential or possibility of something happening

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate potential or possibility

    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
     Ing
    -0.69
    washer
    -0.61
    kar
    -0.60
    building
    -0.57
     Cortex
    -0.57
    OVA
    -0.57
    ging
    -0.56
     honors
    -0.56
    furt
    -0.56
    Maker
    -0.55
    POSITIVE LOGITS
     feas
    1.20
    ĸļ
    1.07
    berra
    1.05
    adian
    1.01
     theoretically
    0.96
     conclud
    0.96
     conce
    0.95
    ÃĥÃĤ
    0.92
     tremend
    0.91
     hypot
    0.88
    Activations Density 0.089%

    No Known Activations