© 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. 10-RES-JB
    11. 11540
    Prev
    Next
    INDEX
    Explanations

    future intentions or plans mentioned in a negative light

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating improbability or denial of occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guessing
    -0.69
    OTO
    -0.68
     refusing
    -0.67
    cule
    -0.67
     pledging
    -0.66
     likened
    -0.65
     withholding
    -0.65
     vowed
    -0.65
     gazing
    -0.64
    Reviewer
    -0.64
    POSITIVE LOGITS
     exist
    1.37
     suffice
    1.34
     occur
    1.34
     affect
    1.31
     resonate
    1.25
     happen
    1.24
     succeed
    1.24
     survive
    1.14
    exist
    1.12
     translate
    1.10
    Activations Density 0.265%

    No Known Activations