© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1-RES-JB
    11. 23985
    Prev
    Next
    INDEX
    Explanations

    specific acronyms or identifiers related to news organizations or events

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "SB" identifiers or codes

    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
     Warfare
    -0.65
     plur
    -0.63
    omorphic
    -0.62
    ghan
    -0.62
     wake
    -0.61
    iasis
    -0.60
     colonial
    -0.60
     Hiroshima
    -0.59
    ocard
    -0.59
     Camb
    -0.58
    POSITIVE LOGITS
    SB
    1.40
    BM
    0.85
     SB
    0.84
    ORTS
    0.84
    HB
    0.77
    BA
    0.76
    ugg
    0.76
    BG
    0.76
    soType
    0.75
    ITS
    0.74
    Activations Density 0.007%

    No Known Activations