© 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. 0-RES-JB
    11. 6285
    Prev
    Next
    INDEX
    Explanations

    words related to polarity

    oai_token-act-pair · gpt-3.5-turbo

    references to polar and non-polar substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TD
    -0.69
     mustard
    -0.68
     eff
    -0.66
     spe
    -0.64
     throw
    -0.62
     TDs
    -0.61
    ãģ§
    -0.61
     stuffing
    -0.61
     cab
    -0.61
     Bom
    -0.61
    POSITIVE LOGITS
    olar
    4.82
    olars
    3.11
    oles
    1.57
    ipolar
    1.22
    olt
    1.21
    olin
    1.20
     Polar
    1.18
    olit
    1.16
    ole
    1.12
    olas
    1.11
    Activations Density 0.008%

    No Known Activations