© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7801
    Prev
    Next
    INDEX
    Explanations

    comments, remarks, and words mentioned or quoted in statements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of public commentary or statements

    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
    iencies
    -0.93
    romeda
    -0.79
     Flavoring
    -0.74
    Compat
    -0.73
    addons
    -0.72
    product
    -0.69
    scope
    -0.68
    effic
    -0.68
    isoft
    -0.68
    Tier
    -0.67
    POSITIVE LOGITS
     uttered
    1.52
     louder
    1.17
     conveyed
    1.09
     aloud
    1.09
     spoken
    1.03
     echoed
    1.00
     phrases
    0.97
     voic
    0.97
     audible
    0.96
     scrib
    0.95
    Activations Density 0.720%

    No Known Activations