© 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. 2-RES-JB
    11. 11147
    Prev
    Next
    INDEX
    Explanations

    mentions of "Illy" with varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Silly"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERTISEMENT
    -0.75
    lished
    -0.73
    ATTLE
    -0.73
    estation
    -0.66
    İĭ
    -0.66
    krit
    -0.65
     RTX
    -0.64
    itivity
    -0.63
    heses
    -0.61
    orers
    -0.61
    POSITIVE LOGITS
    illy
    0.92
    uminati
    0.83
    ield
    0.81
    iard
    0.80
    espie
    0.69
     Circus
    0.68
    yy
    0.68
     externalToEVAOnly
    0.65
    xtap
    0.65
    inois
    0.65
    Activations Density 0.007%

    No Known Activations