© 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. 8-RES-JB
    11. 6858
    Prev
    Next
    INDEX
    Explanations

    names of people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     audition
    -0.70
     CFL
    -0.64
    interstitial
    -0.63
     fixtures
    -0.62
     lockout
    -0.61
     pickup
    -0.60
     clubhouse
    -0.60
    SELECT
    -0.59
    atown
    -0.58
    FORMATION
    -0.58
    POSITIVE LOGITS
     argues
    0.86
     proverb
    0.84
     et
    0.80
    Econom
    0.80
    maxwell
    0.80
     concludes
    0.77
     gmaxwell
    0.77
     observes
    0.75
     recommends
    0.75
     (@
    0.74
    Activations Density 0.740%

    No Known Activations