© 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. 4-RES-JB
    11. 10366
    Prev
    Next
    INDEX
    Explanations

    words related to computer terms or issues

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rep" and its variations, likely related to repetitions or reports

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

    No Comments

    Negative Logits
    istically
    -0.75
     Galile
    -0.66
    BuyableInstoreAndOnline
    -0.65
     Brist
    -0.64
     Keane
    -0.62
     Ibn
    -0.61
     Mou
    -0.61
     Ashe
    -0.61
     Bridges
    -0.60
     Garc
    -0.60
    POSITIVE LOGITS
    ublic
    1.63
    rint
    1.22
    resents
    1.17
    orters
    1.14
    atri
    1.13
    utation
    1.04
    rising
    1.00
    ossession
    1.00
    ulse
    1.00
    ression
    0.99
    Activations Density 0.010%

    No Known Activations