© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20726
    Prev
    Next
    INDEX
    Explanations

    phrases within quotations to express strong emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    quoted statements expressing strong emotions or reactions

    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
    tein
    -0.71
    omorphic
    -0.70
    icular
    -0.70
    paren
    -0.67
    Ļ½
    -0.67
    stant
    -0.67
    ulic
    -0.66
    ackets
    -0.66
    elta
    -0.65
    ¾
    -0.64
    POSITIVE LOGITS
    /"
    0.92
    alos
    0.65
    >>\
    0.64
     Griff
    0.63
     AAP
    0.62
     remark
    0.60
     revealing
    0.60
    ãģ®ç
    0.59
     recommending
    0.59
    sic
    0.58
    Activations Density 0.075%

    No Known Activations