© 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. 8-RES-JB
    11. 19304
    Prev
    Next
    INDEX
    Explanations

    mentions of the present time or current circumstances

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of the present, highlighting its significance in various contexts

    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
    isexual
    -0.82
    uddin
    -0.75
    kick
    -0.74
    jit
    -0.73
    maxwell
    -0.67
     Leban
    -0.66
    issy
    -0.64
     Dres
    -0.64
     spilled
    -0.64
    jar
    -0.63
    POSITIVE LOGITS
    iment
    1.11
     tense
    1.05
     invention
    0.97
    eering
    0.90
    iments
    0.89
     incarnation
    0.83
     century
    0.76
     day
    0.76
    ebin
    0.72
     predicament
    0.71
    Activations Density 0.018%

    No Known Activations