© 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. 11-RES-JB
    11. 22444
    Prev
    Next
    INDEX
    Explanations

    misinterpretations or errors in information

    oai_token-act-pair · gpt-3.5-turbo

    references to mistakes or errors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.80
     Liberation
    -0.74
    joy
    -0.74
    女
    -0.69
     Crush
    -0.69
     solidarity
    -0.69
     Fight
    -0.68
    cend
    -0.65
     liberating
    -0.65
     Reson
    -0.64
    POSITIVE LOGITS
     incorrectly
    1.96
     incorrect
    1.87
     misinterpret
    1.84
     improperly
    1.80
     erroneous
    1.77
     inaccur
    1.77
     mistakenly
    1.76
     overest
    1.73
     errone
    1.72
     inaccurate
    1.72
    Activations Density 0.687%

    No Known Activations