© 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. 9-RES-JB
    11. 5503
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contradicting statements or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    instances of contrasting or contradictory statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cellaneous
    -0.75
    --+
    -0.67
     Pwr
    -0.63
    ished
    -0.62
    ablishment
    -0.61
    iqueness
    -0.60
    Gene
    -0.59
    ileged
    -0.59
    icultural
    -0.59
    legates
    -0.58
    POSITIVE LOGITS
     reality
    1.15
     truth
    1.09
     actually
    1.01
     actual
    0.89
    reality
    0.88
    Actually
    0.87
    agine
    0.86
     Actually
    0.85
     Reality
    0.85
    actually
    0.84
    Activations Density 0.317%

    No Known Activations