© 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. 9243
    Prev
    Next
    INDEX
    Explanations

    individuals or entities that are in a position of leadership or authority

    oai_token-act-pair · gpt-3.5-turbo

    individuals or organizations that hold leadership roles

    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
     pretext
    -0.72
     corrupt
    -0.70
     deval
    -0.67
     KGB
    -0.67
     dishon
    -0.67
     utter
    -0.66
     unanim
    -0.64
    ghazi
    -0.63
     unbeliev
    -0.62
     obliter
    -0.61
    POSITIVE LOGITS
    é¾
    0.79
    enegger
    0.72
    nutrition
    0.68
    ocado
    0.67
    nw
    0.65
     advocacy
    0.65
     www
    0.65
     sustainability
    0.65
    MAP
    0.65
     challeng
    0.64
    Activations Density 0.807%

    No Known Activations