© 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. 1619
    Prev
    Next
    INDEX
    Explanations

    mentions of specific technologies or software components related to computing and information technology

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    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
    elle
    -0.67
    erie
    -0.66
    ummer
    -0.65
    >[
    -0.64
     Voters
    -0.63
    amera
    -0.63
    perties
    -0.61
    Report
    -0.60
    agara
    -0.60
     Reporter
    -0.59
    POSITIVE LOGITS
     other
    0.82
    rogen
    0.80
     thus
    0.79
     hence
    0.79
     optionally
    0.77
     thereby
    0.75
     thence
    0.73
    rogens
    0.72
     ITS
    0.71
     its
    0.70
    Activations Density 0.397%

    No Known Activations