© 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. 8-RES-JB
    11. 3218
    Prev
    Next
    INDEX
    Explanations

    words related to causality or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    references to the subject 'it' and its consequences or characteristics

    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
    jri
    -0.77
    į
    -0.66
    amaz
    -0.66
    itive
    -0.65
    stellar
    -0.65
    eworthy
    -0.64
     Atkinson
    -0.63
    west
    -0.63
    piring
    -0.63
     Stern
    -0.61
    POSITIVE LOGITS
    'll
    0.99
     ought
    0.93
    're
    0.91
    've
    0.90
    'd
    0.89
     cannot
    0.88
     could
    0.87
     shouldn
    0.86
     should
    0.85
     might
    0.84
    Activations Density 0.301%

    No Known Activations