© 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. 11-RES-JB
    11. 9310
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching for solutions or agreements

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of searching or discovering solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idium
    -0.84
    panic
    -0.83
    ossession
    -0.77
    upt
    -0.77
    ember
    -0.75
    oct
    -0.71
    STER
    -0.71
    yip
    -0.70
    ICO
    -0.69
    search
    -0.67
    POSITIVE LOGITS
     ways
    1.49
     solutions
    1.32
     effic
    1.21
     replacements
    1.20
     somew
    1.14
     alternatives
    1.11
     loopholes
    1.11
     cures
    1.04
     avenues
    1.04
     mechanisms
    0.98
    Activations Density 0.116%

    No Known Activations