© 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. 23670
    Prev
    Next
    INDEX
    Explanations

    references to specific people or events, especially related to announcements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or events in sports and culture

    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
     keyboards
    -0.57
     slur
    -0.51
     fuzz
    -0.51
     Occasionally
    -0.51
     thyroid
    -0.47
     tidy
    -0.46
     innocuous
    -0.45
     manic
    -0.44
     feminine
    -0.44
     stereotype
    -0.44
    POSITIVE LOGITS
    cember
    0.63
    OUP
    0.60
    ETHOD
    0.59
    numbered
    0.58
    DonaldTrump
    0.57
    HQ
    0.55
    itialized
    0.54
    DEM
    0.54
    razil
    0.54
    ģ«
    0.53
    Activations Density 2.629%

    No Known Activations