© 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. 802
    Prev
    Next
    INDEX
    Explanations

    words related to struggles or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of words and phrases related to economic or systemic problems

    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
     authenticated
    -0.73
     towed
    -0.71
     promot
    -0.70
     learners
    -0.70
     specially
    -0.68
     logged
    -0.68
     disabled
    -0.68
     dj
    -0.67
     platinum
    -0.66
     recre
    -0.66
    POSITIVE LOGITS
    umbling
    1.08
    ithering
    1.03
    umption
    1.03
    inges
    1.02
    ounding
    1.00
    aution
    0.99
    akings
    0.97
    risis
    0.95
    attering
    0.95
    arth
    0.95
    Activations Density 0.164%

    No Known Activations