© 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. 1-RES-JB
    11. 24060
    Prev
    Next
    INDEX
    Explanations

    mention of the action of selling or promoting something persistently or aggressively

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "peddling" and its variations, particularly in contexts relating to the distribution or promotion of ideas or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARB
    -0.66
     Palm
    -0.64
    ARY
    -0.63
     ESA
    -0.63
     Origin
    -0.62
     Audit
    -0.62
     Fraser
    -0.62
     Biological
    -0.61
     Feder
    -0.61
     Carbuncle
    -0.60
    POSITIVE LOGITS
     pedd
    1.57
     nodd
    0.90
     mathemat
    0.88
    querque
    0.85
    eering
    0.84
    ulum
    0.80
    inson
    0.80
    ication
    0.78
    wagon
    0.78
    rette
    0.76
    Activations Density 0.012%

    No Known Activations