© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7266
    Prev
    Next
    INDEX
    Explanations

    negative statements about the quality or condition of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of negativity or concerns about quality

    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
    albeit
    -0.66
    oso
    -0.62
    irie
    -0.60
    endix
    -0.59
    rather
    -0.58
    empt
    -0.58
    003
    -0.57
    uddin
    -0.57
     kindred
    -0.56
    alm
    -0.55
    POSITIVE LOGITS
     anymore
    1.78
     nor
    1.47
     either
    1.20
     whatsoever
    1.12
     anywhere
    0.98
    nor
    0.97
     unless
    0.90
     Enough
    0.88
     enough
    0.88
     anything
    0.87
    Activations Density 0.219%

    No Known Activations