© 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. 5094
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "tribute" or similar notions of acknowledgment or dedication

    oai_token-act-pair · gpt-3.5-turbo

    references to rib-related content or discussions

    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
    terday
    -0.69
    FORE
    -0.66
     Serious
    -0.64
     Anders
    -0.60
    TPS
    -0.60
     Graham
    -0.60
     Sunny
    -0.60
     harbour
    -0.59
    ################
    -0.58
    izations
    -0.58
    POSITIVE LOGITS
    ril
    1.05
    unal
    1.04
    orough
    0.98
    leness
    0.96
    bon
    0.96
    bled
    0.93
    bage
    0.93
    raph
    0.92
    bles
    0.92
    ulations
    0.90
    Activations Density 0.030%

    No Known Activations