© 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. 10-RES-JB
    11. 17361
    Prev
    Next
    INDEX
    Explanations

    duplicated letters in words

    oai_token-act-pair · gpt-3.5-turbo

    words associated with humor or silliness

    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
    代
    -0.85
     misunder
    -0.76
     Luthor
    -0.71
    DonaldTrump
    -0.69
    imir
    -0.67
    ewski
    -0.67
    nikov
    -0.66
    itates
    -0.65
     Integrity
    -0.64
    auri
    -0.62
    POSITIVE LOGITS
    gey
    1.24
    zing
    1.20
    ze
    1.17
    gee
    1.15
    zer
    1.12
    zy
    1.09
    zers
    1.06
    zeb
    1.06
    zie
    1.04
    leans
    1.02
    Activations Density 0.045%

    No Known Activations