© 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. 6660
    Prev
    Next
    INDEX
    Explanations

    verbs related to splitting or separating

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "diverge" and its variations in context

    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
     Citation
    -0.71
    ellen
    -0.70
    ammy
    -0.68
    terday
    -0.68
    EEK
    -0.65
     Rivals
    -0.63
     Butterfly
    -0.61
     Immunity
    -0.60
    eden
    -0.60
    omnia
    -0.59
    POSITIVE LOGITS
    gent
    1.72
    gence
    1.57
    gently
    1.41
    tic
    1.35
    gencies
    1.32
    ging
    1.29
    ged
    1.24
    gency
    1.23
    ting
    1.17
    ge
    1.13
    Activations Density 0.052%

    No Known Activations