© 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. 10-RES-JB
    11. 14171
    Prev
    Next
    INDEX
    Explanations

    words related to influence and its different forms

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to influence and impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    audi
    -0.73
    pelled
    -0.69
    unic
    -0.67
    kies
    -0.66
    ci
    -0.65
    ccoli
    -0.64
    owler
    -0.63
    wart
    -0.63
    uni
    -0.62
    bestos
    -0.62
    POSITIVE LOGITS
     outcome
    1.65
     outcomes
    1.46
     decisions
    1.37
     trajectory
    1.29
     behavior
    1.27
     behaviour
    1.24
     destiny
    1.20
     perception
    1.20
     decision
    1.19
     perceptions
    1.17
    Activations Density 0.287%

    No Known Activations