© 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. 7-RES-JB
    11. 8501
    Prev
    Next
    INDEX
    Explanations

    occurrences of multiple entities joining a specific event or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to joining or accompanying people in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Origin
    -0.71
     relevance
    -0.69
     leverage
    -0.65
    urai
    -0.64
     inacc
    -0.63
     hindsight
    -0.63
     foreskin
    -0.63
     Confeder
    -0.62
     allowable
    -0.61
     RELE
    -0.59
    POSITIVE LOGITS
    by
    1.12
     by
    1.03
    hani
    0.92
    By
    0.90
     BY
    0.84
    Ń·
    0.84
    ById
    0.80
    ãĤ¡
    0.80
    BY
    0.79
     aback
    0.79
    Activations Density 0.202%

    No Known Activations