© 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. 7-RES-JB
    11. 23601
    Prev
    Next
    INDEX
    Explanations

    mentions of specific policy schemes or programs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various schemes or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Flo
    -0.68
    ãģĹ
    -0.64
    inas
    -0.64
    azines
    -0.63
    Nob
    -0.62
     Brah
    -0.62
     Qiao
    -0.59
     Flo
    -0.58
     Clover
    -0.57
    lean
    -0.56
    POSITIVE LOGITS
     schemes
    1.09
     scheme
    1.03
    etary
    0.90
     devised
    0.86
    eers
    0.83
    ĸļ
    0.80
    eering
    0.77
    udeb
    0.76
    ulence
    0.76
     Scheme
    0.71
    Activations Density 0.015%

    No Known Activations