© 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. 1-RES-JB
    11. 5050
    Prev
    Next
    INDEX
    Explanations

    names with the specific pattern of 'err' in the middle

    oai_token-act-pair · gpt-3.5-turbo

    mentions of errors or issues related to a specific context, likely in a sports or entertainment setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥
    -0.74
    ı
    -0.67
    İ
    -0.67
    ĺħ
    -0.67
    figure
    -0.65
    ±
    -0.65
    Ķ
    -0.64
    esthetic
    -0.64
    ķ
    -0.62
    rooms
    -0.61
    POSITIVE LOGITS
    untled
    1.06
    err
    0.90
    idge
    0.90
    anger
    0.89
    andom
    0.87
    rr
    0.86
    ionage
    0.85
    awei
    0.85
    antly
    0.84
    iott
    0.83
    Activations Density 0.009%

    No Known Activations