© 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. 10-RES-JB
    11. 2696
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Chart", with a preference for higher activations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "chart" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Romeo
    -0.68
    ignt
    -0.66
    vae
    -0.64
    IRE
    -0.61
     Paulo
    -0.60
     Cic
    -0.60
     Chinatown
    -0.59
     LIMITED
    -0.59
    cknow
    -0.58
     Goodman
    -0.57
    POSITIVE LOGITS
    ered
    1.32
    ued
    1.06
    ing
    0.90
    erer
    0.90
    uing
    0.86
    ed
    0.86
    erers
    0.84
    chart
    0.82
    icle
    0.80
    eer
    0.80
    Activations Density 0.033%

    No Known Activations