© 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. 6549
    Prev
    Next
    INDEX
    Explanations

    dates and time-related terms

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and numerical references

    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
    hap
    -0.93
     HL
    -0.92
    Hu
    -0.83
     horm
    -0.83
     vulner
    -0.81
    HK
    -0.80
     Himal
    -0.78
     Hak
    -0.78
     GH
    -0.77
     Hass
    -0.76
    POSITIVE LOGITS
    ner
    1.00
    olate
    0.83
    2016
    0.83
    uton
    0.83
    ating
    0.82
    ATE
    0.81
    bane
    0.81
    rators
    0.81
    idden
    0.81
    board
    0.81
    Activations Density 0.267%

    No Known Activations