© 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. 3-RES-JB
    11. 12109
    Prev
    Next
    INDEX
    Explanations

    words related to numerical figures or representations like 'fig 10' and 'figure 4'

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical figures or data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    answered
    -0.72
     Ces
    -0.65
    keyes
    -0.62
     Sussex
    -0.61
     Eug
    -0.61
    TPPStreamerBot
    -0.60
     Remain
    -0.60
     Dominic
    -0.59
    atches
    -0.59
     Wake
    -0.59
    POSITIVE LOGITS
    uration
    1.13
    fig
    0.96
    lisher
    0.95
    urations
    0.89
    ures
    0.88
    uring
    0.86
    figure
    0.81
    mentation
    0.81
    lio
    0.80
     fig
    0.79
    Activations Density 0.008%

    No Known Activations