© 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. 1-RES-JB
    11. 3223
    Prev
    Next
    INDEX
    Explanations

    financial figures and symbols, particularly currencies and numbers

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols, particularly those associated with currency and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.41
     Salman
    -0.30
    cknow
    -0.28
     Maxwell
    -0.28
    odynam
    -0.27
     WATCHED
    -0.27
    ographical
    -0.27
     Pv
    -0.26
    bard
    -0.26
     secretive
    -0.26
    POSITIVE LOGITS
    hower
    0.39
    idth
    0.35
    iversary
    0.35
    antha
    0.34
    okane
    0.34
     lasted
    0.34
    éĹĺ
    0.34
    ulous
    0.33
    ETHOD
    0.32
     conclud
    0.32
    Activations Density 1.054%

    No Known Activations