© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 13969
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names, particularly first names

    oai_token-act-pair · gpt-3.5-turbo

    the term "Col" followed by numerical identifiers, likely indicating colleges or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ducks
    -0.67
     Werewolf
    -0.65
     forth
    -0.64
     retract
    -0.60
     Canucks
    -0.59
     derog
    -0.58
     Californ
    -0.57
     puck
    -0.57
    Language
    -0.57
    doors
    -0.56
    POSITIVE LOGITS
    ossal
    1.49
    ombo
    1.35
    umbo
    1.27
    leen
    1.27
    onel
    1.25
    onial
    1.18
    ophon
    1.17
    oured
    1.11
    angelo
    1.07
    ored
    1.02
    Activations Density 0.014%

    No Known Activations