© 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. 8-RES-JB
    11. 3148
    Prev
    Next
    INDEX
    Explanations

    specific mentions of certain ordinal positions within a series or sequence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significance or prominence

    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
     sucks
    -0.76
    enery
    -0.73
    pathy
    -0.69
    hm
    -0.69
    ieties
    -0.68
    linux
    -0.68
    books
    -0.64
    join
    -0.64
    nir
    -0.64
    apache
    -0.62
    POSITIVE LOGITS
     culmination
    1.28
     largest
    1.19
     longest
    1.18
     centerpiece
    1.18
     latest
    1.09
     heaviest
    1.07
     biggest
    1.05
     oldest
    1.05
     fastest
    1.05
     widest
    1.03
    Activations Density 0.253%

    No Known Activations