© 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. 8-RES-JB
    11. 2745
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical data in text

    oai_token-act-pair · gpt-3.5-turbo

    percentages, especially in the context of surveys and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Redd
    -0.71
    ãĤ´ãĥ³
    -0.69
    eworld
    -0.68
    venge
    -0.67
    jri
    -0.65
    laden
    -0.64
     champ
    -0.62
     fame
    -0.62
    vised
    -0.62
     riches
    -0.62
    POSITIVE LOGITS
     respondents
    1.05
     percent
    0.89
     Australians
    0.84
     Americans
    0.82
     Britons
    0.82
     Canadians
    0.77
     Percent
    0.76
     disapprove
    0.76
     polled
    0.74
    percent
    0.74
    Activations Density 0.109%

    No Known Activations