© 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. 5007
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the utilization of items or entities for specific purposes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "used."

    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
     Hai
    -0.78
    bitious
    -0.70
     Roose
    -0.65
    nesty
    -0.61
     Niet
    -0.60
    alos
    -0.60
     Pis
    -0.60
     undertaking
    -0.58
     Rid
    -0.57
     Gord
    -0.57
    POSITIVE LOGITS
     sparing
    1.11
    fully
    0.92
     interchange
    0.91
     captcha
    0.80
    pez
    0.79
     extensively
    0.78
     exclusively
    0.77
    FUL
    0.74
     wisely
    0.73
    ragon
    0.72
    Activations Density 0.075%

    No Known Activations