© 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. 1-RES-JB
    11. 9489
    Prev
    Next
    INDEX
    Explanations

    words related to agreements or treaties

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "accord."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ################
    -0.71
    bull
    -0.63
     Roof
    -0.63
    prototype
    -0.62
     Ty
    -0.62
    dden
    -0.62
    ³³³³³³³³³³³³³³³³
    -0.62
     Karl
    -0.60
    APD
    -0.60
     Cycl
    -0.59
    POSITIVE LOGITS
     accord
    1.31
     Accord
    0.99
    awaru
    0.98
    ords
    0.96
    itures
    0.95
    romeda
    0.89
    reement
    0.89
     Harmony
    0.87
    endi
    0.85
    inet
    0.85
    Activations Density 0.005%

    No Known Activations