© 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. 7-RES-JB
    11. 18841
    Prev
    Next
    INDEX
    Explanations

    specific strings of characters that likely indicate a pattern or code

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "lie" and related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omorphic
    -0.71
     Alban
    -0.67
     Gmail
    -0.67
     civilian
    -0.65
     Skydragon
    -0.63
    è¦ļéĨĴ
    -0.59
     Kaf
    -0.57
     oun
    -0.57
     Alph
    -0.56
     Tucson
    -0.56
    POSITIVE LOGITS
    lights
    0.74
    ski
    0.73
    else
    0.73
    s
    0.70
    tu
    0.70
    mean
    0.69
    sure
    0.69
    own
    0.69
    mand
    0.66
    thy
    0.66
    Activations Density 0.288%

    No Known Activations