© 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. 3072
    Prev
    Next
    INDEX
    Explanations

    coding or special characters, such as symbols and arrows

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific symbol or character

    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
     shelf
    -0.68
     plain
    -0.67
    ifice
    -0.66
     Gorge
    -0.64
     Bombs
    -0.64
     disposable
    -0.62
     DOT
    -0.62
     coffin
    -0.61
     Spit
    -0.61
     conflic
    -0.61
    POSITIVE LOGITS
    especially
    0.96
    then
    0.88
    particularly
    0.84
    said
    0.82
    which
    0.79
    _>
    0.79
    unknown
    0.77
    ¹
    0.77
    £
    0.76
    insert
    0.76
    Activations Density 0.101%

    No Known Activations