© 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. 11-RES-JB
    11. 7039
    Prev
    Next
    INDEX
    Explanations

    the word "Cas" followed by different numbers

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Cas" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĺħ
    -0.67
     victorious
    -0.66
    doms
    -0.63
     stakes
    -0.58
     fielding
    -0.57
    hood
    -0.54
     attainment
    -0.53
     hurdles
    -0.53
     sentient
    -0.52
     indebted
    -0.52
    POSITIVE LOGITS
    anova
    1.44
    imir
    1.44
    hews
    1.27
    bah
    1.26
    hew
    1.23
    illas
    1.16
    sell
    1.14
    sels
    1.13
    ework
    1.08
    grain
    1.06
    Activations Density 0.027%

    No Known Activations