© 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. 13786
    Prev
    Next
    INDEX
    Explanations

    terms related to interest in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to interest, support, and the evaluation of situations or conditions

    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
    /,
    -0.70
     ___
    -0.64
    :(
    -0.62
    olor
    -0.58
     whine
    -0.57
    ???
    -0.57
     Pulitzer
    -0.56
     whining
    -0.56
     redacted
    -0.55
     Thanksgiving
    -0.54
    POSITIVE LOGITS
     of
    0.81
     organised
    0.80
     learnt
    0.77
     util
    0.76
     organis
    0.75
     organisation
    0.75
     towards
    0.73
     organisers
    0.73
     envis
    0.70
     favourable
    0.70
    Activations Density 0.532%

    No Known Activations