© 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. 4-RES-JB
    11. 255
    Prev
    Next
    INDEX
    Explanations

    words related to communication and transmission

    oai_token-act-pair · gpt-3.5-turbo

    words related to the act of conveying or communicating information

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

    No Comments

    Negative Logits
    liga
    -0.84
    atti
    -0.76
     Alban
    -0.73
    anova
    -0.73
    ofi
    -0.70
    este
    -0.68
     Treasurer
    -0.68
    âĵĺ
    -0.67
    makers
    -0.62
     Bav
    -0.61
    POSITIVE LOGITS
     transmitted
    0.84
     transmissions
    0.82
     transmit
    0.75
     transmission
    0.74
     behavi
    0.72
    sov
    0.69
    chnology
    0.69
    forward
    0.69
    ivity
    0.68
    ency
    0.67
    Activations Density 0.010%

    No Known Activations