© 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. 3139
    Prev
    Next
    INDEX
    Explanations

    phrases related to direct competition or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing competition or match-style events

    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
    nces
    -0.66
     recip
    -0.64
     Byzantine
    -0.63
    ilial
    -0.62
    nan
    -0.62
    icity
    -0.62
    cial
    -0.61
    conn
    -0.61
    tsky
    -0.60
    DOM
    -0.59
    POSITIVE LOGITS
    quarters
    0.85
     shoulders
    0.78
    quartered
    0.73
     heels
    0.67
     tails
    0.65
    Exit
    0.65
     scissors
    0.62
    arted
    0.60
    ache
    0.58
     shove
    0.58
    Activations Density 0.083%

    No Known Activations