© 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. 0-RES-JB
    11. 6232
    Prev
    Next
    INDEX
    Explanations

    words related to influence or impact

    oai_token-act-pair · gpt-3.5-turbo

    references to influence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cms
    -0.85
    ney
    -0.73
     filing
    -0.69
     filed
    -0.69
    hooting
    -0.68
    idel
    -0.68
    piece
    -0.66
    ãģĵ
    -0.63
    Items
    -0.61
    unny
    -0.61
    POSITIVE LOGITS
     influence
    3.82
     Influence
    2.83
     influences
    2.46
     influencing
    2.05
     sway
    1.81
     influenced
    1.78
     impact
    1.54
     clout
    1.51
     affect
    1.51
     Influ
    1.42
    Activations Density 0.022%

    No Known Activations