© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3549
    Prev
    Next
    INDEX
    Explanations

    phrases related to the hawk bird or politics

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups associated with the term "hawk"

    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
     Incarnation
    -0.76
     Result
    -0.75
     Investigator
    -0.75
     Mysteries
    -0.75
     Myster
    -0.73
     Ritual
    -0.71
    URE
    -0.70
     Framework
    -0.70
     Investigators
    -0.69
     Mankind
    -0.68
    POSITIVE LOGITS
     haw
    1.62
    keye
    1.35
     hawk
    1.18
    kish
    1.16
    keyes
    0.98
    aii
    0.92
    alus
    0.88
    haw
    0.84
    indal
    0.82
     greens
    0.81
    Activations Density 0.007%

    No Known Activations