© 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. 10603
    Prev
    Next
    INDEX
    Explanations

    statements that the neuron perceives to be true or accurate

    oai_token-act-pair · gpt-3.5-turbo

    phrases asserting the truthfulness of statements

    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
    uled
    -0.75
    adish
    -0.72
    rador
    -0.71
    acent
    -0.68
    aida
    -0.68
    hens
    -0.68
    asers
    -0.68
    ADRA
    -0.68
    onut
    -0.66
     Citiz
    -0.65
    POSITIVE LOGITS
     believers
    0.86
    hood
    0.84
     regardless
    0.78
     believer
    0.76
     insofar
    0.72
     irrespective
    0.70
     portrayal
    0.69
    terday
    0.68
    izable
    0.68
     everywhere
    0.68
    Activations Density 0.023%

    No Known Activations