© 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. 10-RES-JB
    11. 7839
    Prev
    Next
    INDEX
    Explanations

    specific sequences of events, possibly related to a crime or investigation

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and connective phrases that link statements or actions

    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
    eatures
    -0.71
    Critics
    -0.70
    eaturing
    -0.69
    ¿½
    -0.66
    ocre
    -0.65
    Score
    -0.64
    blem
    -0.63
     srfAttach
    -0.63
    lif
    -0.63
     exceptions
    -0.62
    POSITIVE LOGITS
     decided
    1.29
     rushed
    1.13
     alerted
    1.11
     hurried
    1.10
     immediately
    1.06
     instinctively
    1.03
     contacted
    1.03
     promptly
    0.99
     wanted
    0.99
     reacted
    0.99
    Activations Density 0.371%

    No Known Activations