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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 14167
    Prev
    Next
    INDEX
    Explanations

    timestamps in text

    oai_token-act-pair · gpt-3.5-turbo

    time and date indicators, as well as terms related to rarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.67
    ffield
    -0.67
    ignment
    -0.67
    itiz
    -0.66
     spons
    -0.64
     buffs
    -0.61
     preservation
    -0.61
    fts
    -0.60
    gettable
    -0.60
    isable
    -0.60
    POSITIVE LOGITS
    <|endoftext|>
    0.76
     âĢº
    0.73
    MENTS
    0.72
    ||
    0.72
     NOTE
    0.69
    ENN
    0.68
     Thanks
    0.68
    Posted
    0.67
     DEFENSE
    0.67
     Edited
    0.67
    Activations Density 0.018%

    No Known Activations