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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 11683
    Prev
    Next
    INDEX
    Explanations

    phrases related to the town of Toms

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "tom" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chnology
    -0.71
    lance
    -0.68
    ries
    -0.66
    whe
    -0.62
    ABLE
    -0.61
    acts
    -0.61
     judges
    -0.60
     Heist
    -0.60
    brates
    -0.58
    ARD
    -0.57
    POSITIVE LOGITS
    pring
    1.38
    chool
    1.26
    paces
    1.26
    creen
    1.23
    hift
    1.22
    mith
    1.19
    pace
    1.14
    ocial
    1.14
    kaya
    1.13
    ayer
    1.12
    Activations Density 0.050%

    No Known Activations