© 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. 10-RES-JB
    11. 11316
    Prev
    Next
    INDEX
    Explanations

    hyperlinks ending in '/'

    oai_token-act-pair · gpt-3.5-turbo

    instances of slashes or forward slashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sanct
    -0.65
    iosyncr
    -0.63
     throne
    -0.63
     Opportun
    -0.62
     duel
    -0.61
     REAL
    -0.61
     waiting
    -0.60
     lobb
    -0.60
     saving
    -0.60
     dece
    -0.60
    POSITIVE LOGITS
    CN
    0.95
    o
    0.92
    HI
    0.91
    vc
    0.90
    AH
    0.86
    RH
    0.86
    oa
    0.85
    Lt
    0.84
    WT
    0.84
    CIA
    0.84
    Activations Density 0.020%

    No Known Activations