© 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. 21630
    Prev
    Next
    INDEX
    Explanations

    prompts or invitations like "Want" for further information or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a desire or request for information or action

    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
    é¾
    -0.70
    cise
    -0.68
    chnology
    -0.66
    cision
    -0.66
     slopes
    -0.65
    ĪĴ
    -0.65
     Seym
    -0.65
    é¾įå¥ij士
    -0.64
    à¼
    -0.63
    issance
    -0.63
    POSITIVE LOGITS
    reprene
    0.84
    atile
    0.79
    ful
    0.77
    lessly
    0.72
    only
    0.72
    htar
    0.71
    fully
    0.71
    anta
    0.70
    igslist
    0.70
     poster
    0.64
    Activations Density 0.050%

    No Known Activations