© 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. 10-RES-JB
    11. 3464
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Tor" followed by a number ranging from 7 to 10

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Tor" and related variations indicating its significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naires
    -0.82
     Dakota
    -0.70
     Eisenhower
    -0.63
    ãħĭ
    -0.63
    ãħĭãħĭ
    -0.62
    arden
    -0.61
     Fif
    -0.61
     Continental
    -0.60
     Baldwin
    -0.60
     Hawaiian
    -0.58
    POSITIVE LOGITS
    mented
    1.30
    rance
    1.17
    onto
    1.14
    sten
    1.05
    reon
    1.02
    rent
    1.01
    rington
    0.97
    bj
    0.97
    rid
    0.94
    rence
    0.94
    Activations Density 0.028%

    No Known Activations