© 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. 18833
    Prev
    Next
    INDEX
    Explanations

    proper nouns or words that seem to be nonsense

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "um" in various forms

    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
     blackout
    -0.66
     sober
    -0.60
     strawberries
    -0.57
     stranger
    -0.57
     lure
    -0.56
     Cuomo
    -0.56
     cutoff
    -0.55
     Barney
    -0.54
     heater
    -0.54
     wool
    -0.53
    POSITIVE LOGITS
    pty
    1.30
    ming
    1.25
    mers
    1.18
    ulative
    1.11
    brance
    1.04
    vir
    1.03
    etric
    1.02
    pt
    0.98
    acher
    0.97
    mary
    0.97
    Activations Density 0.057%

    No Known Activations