© 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. 23455
    Prev
    Next
    INDEX
    Explanations

    superlatives, especially the suffix "-est."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pedestrian" and its variations

    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
    perty
    -0.77
    veyard
    -0.73
    shock
    -0.72
     tremend
    -0.70
    ppo
    -0.69
    chwitz
    -0.68
    senal
    -0.68
    pton
    -0.66
    hammer
    -0.64
    sterdam
    -0.64
    POSITIVE LOGITS
    ruct
    0.99
    imating
    0.97
    imates
    0.97
    imate
    0.95
    ream
    0.94
    alker
    0.93
    reet
    0.90
    imated
    0.85
    osterone
    0.83
    eal
    0.82
    Activations Density 0.026%

    No Known Activations