© 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. 9532
    Prev
    Next
    INDEX
    Explanations

    phrases related to negation or exclusion

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and prepositions indicating alternative options or conditions

    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
     horm
    -0.72
    tackle
    -0.68
     Conan
    -0.66
    ETS
    -0.64
    ires
    -0.64
    efer
    -0.63
    nee
    -0.60
    onday
    -0.60
    DragonMagazine
    -0.60
     Reson
    -0.59
    POSITIVE LOGITS
    chard
    1.17
    Else
    1.10
    acles
    1.02
     anything
    1.02
    acle
    1.01
     else
    0.98
    chid
    0.96
    nam
    0.95
     otherwise
    0.91
    ifice
    0.87
    Activations Density 0.125%

    No Known Activations