© 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. 13427
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Abbie"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bie" and its variations

    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
     tense
    -0.70
     suspense
    -0.69
     perpetual
    -0.68
     grid
    -0.67
     tragedies
    -0.66
     meticulous
    -0.66
    arching
    -0.65
     obligated
    -0.65
     pollutants
    -0.64
     terrifying
    -0.64
    POSITIVE LOGITS
    bie
    1.36
    gee
    1.07
    leigh
    0.98
    gment
    0.91
    bies
    0.89
    culosis
    0.86
    yip
    0.85
    lly
    0.84
    vana
    0.84
    gie
    0.84
    Activations Density 0.004%

    No Known Activations