© 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. 3-RES-JB
    11. 7249
    Prev
    Next
    INDEX
    Explanations

    information about the number of times someone has participated or appeared in an event or activity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of appearances in various contexts, particularly related to sports or public events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eor
    -0.75
     Zup
    -0.68
    lass
    -0.68
     ze
    -0.66
    edi
    -0.66
    imb
    -0.65
     mainstream
    -0.65
    warn
    -0.65
    behavior
    -0.64
    kk
    -0.63
    POSITIVE LOGITS
     opener
    0.98
     unbeaten
    0.94
     consecut
    0.81
    IONS
    0.76
    SIGN
    0.75
    earances
    0.74
     interceptions
    0.73
     scorer
    0.73
     outings
    0.72
     appearances
    0.71
    Activations Density 0.097%

    No Known Activations