© 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. 4-RES-JB
    11. 7122
    Prev
    Next
    INDEX
    Explanations

    phrases or words indicating negation or denial

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "ain't," indicating informal or colloquial expressions

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

    No Comments

    Negative Logits
    INC
    -0.70
    Impl
    -0.63
     Agency
    -0.63
    ULT
    -0.62
     Promotion
    -0.62
    =-=-=-=-=-=-=-=-
    -0.62
    EV
    -0.61
    ersen
    -0.61
     Carbuncle
    -0.61
    IAN
    -0.61
    POSITIVE LOGITS
    't
    0.96
     ain
    0.92
    gin
    0.88
     gonna
    0.83
    \\\\\\\\
    0.83
    strument
    0.82
    ãĥ³ãĤ¸
    0.82
    ny
    0.77
    ga
    0.76
    thouse
    0.76
    Activations Density 0.008%

    No Known Activations