© 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. 10-RES-JB
    11. 21658
    Prev
    Next
    INDEX
    Explanations

    names of companies, organizations or entities

    oai_token-act-pair · gpt-3.5-turbo

    special characters and numeric data in various contexts

    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
     laz
    -0.65
     lob
    -0.63
     scar
    -0.62
     bloom
    -0.62
     stranger
    -0.58
     Yelp
    -0.58
     swear
    -0.57
     cursed
    -0.56
     framed
    -0.55
     mound
    -0.55
    POSITIVE LOGITS
    ERT
    0.93
    MAT
    0.89
    ITION
    0.85
    DEV
    0.75
    FER
    0.74
     laureate
    0.74
    ENG
    0.73
    RAL
    0.73
    LET
    0.73
    ITIES
    0.71
    Activations Density 0.335%

    No Known Activations