© 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. 0-RES-JB
    11. 17991
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "SP" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recess
    -0.74
     Ryder
    -0.71
     tant
    -0.68
     Laz
    -0.65
     Dion
    -0.65
     inflated
    -0.63
     cu
    -0.63
     Hilbert
    -0.62
     undone
    -0.62
     Mai
    -0.61
    POSITIVE LOGITS
    SP
    4.01
     SP
    1.98
    sp
    1.66
    SPA
    1.60
    SC
    1.57
    MP
    1.55
    Sp
    1.53
    SL
    1.49
    SM
    1.46
    SN
    1.46
    Activations Density 0.011%

    No Known Activations