© 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. 9-RES-JB
    11. 3094
    Prev
    Next
    INDEX
    Explanations

    numerical sequences

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical identifiers, likely associated with social media or online content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     immedi
    -0.62
     accompl
    -0.59
     commuting
    -0.58
     Palest
    -0.56
     fools
    -0.56
     illegitimate
    -0.55
     superflu
    -0.54
     deadlines
    -0.54
     delic
    -0.54
     thirds
    -0.54
    POSITIVE LOGITS
    CN
    1.02
    sg
    0.98
    dc
    0.98
    df
    0.98
    gz
    0.97
    nl
    0.96
    wm
    0.95
    bc
    0.95
    cv
    0.94
    cm
    0.93
    Activations Density 0.039%

    No Known Activations