© 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. 3184
    Prev
    Next
    INDEX
    Explanations

    words related to searching or hunting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hunt."

    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
    BuyableInstoreAndOnline
    -0.80
    ittered
    -0.73
    DCS
    -0.70
    paying
    -0.69
    atern
    -0.65
    addr
    -0.64
    address
    -0.64
    aples
    -0.61
    iating
    -0.60
    itu
    -0.60
    POSITIVE LOGITS
    hunt
    1.38
     hunts
    1.16
     hunt
    1.12
     Hunt
    1.04
    eers
    1.01
    ãĥ£
    0.98
     hunting
    0.92
     hunter
    0.89
     Hunting
    0.84
     hunted
    0.84
    Activations Density 0.007%

    No Known Activations