© 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. 10154
    Prev
    Next
    INDEX
    Explanations

    phrases related to repeating actions or events

    oai_token-act-pair · gpt-3.5-turbo

    references to time and associated resources

    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
     Cosponsors
    -0.75
     Supports
    -0.74
    addons
    -0.71
     rall
    -0.66
    apons
    -0.66
    Wan
    -0.66
     Marketable
    -0.66
    edom
    -0.64
    habi
    -0.63
    DNA
    -0.63
    POSITIVE LOGITS
     lapse
    0.75
    vity
    0.74
    times
    0.69
    obos
    0.69
     Carbuncle
    0.69
     Chron
    0.68
    onement
    0.68
     expended
    0.68
    consuming
    0.67
     again
    0.66
    Activations Density 0.182%

    No Known Activations