© 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. 8-RES-JB
    11. 24119
    Prev
    Next
    INDEX
    Explanations

    names of companies and media outlets

    oai_token-act-pair · gpt-3.5-turbo

    the presence of common conjunctions and related phrases indicating lists or associations

    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
    ":"/
    -0.78
    HB
    -0.77
    BIP
    -0.71
    autions
    -0.70
    FIG
    -0.68
    hao
    -0.67
    :(
    -0.67
    GOP
    -0.67
    hetamine
    -0.65
    çĭ
    -0.64
    POSITIVE LOGITS
     assorted
    1.11
     others
    1.07
     etc
    1.03
     finally
    0.89
    etc
    0.87
     possibly
    0.75
     optionally
    0.73
     Tus
    0.72
     yes
    0.72
     countless
    0.70
    Activations Density 0.200%

    No Known Activations