© 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. 10083
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases highlighting superiority or preference

    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
    catentry
    -0.90
    ahime
    -0.88
    ulations
    -0.78
    ulative
    -0.72
    enser
    -0.71
    ements
    -0.71
    ulated
    -0.70
    INTON
    -0.69
    uther
    -0.68
    ulators
    -0.68
    POSITIVE LOGITS
     ours
    1.10
     yours
    0.89
     theirs
    0.85
     hers
    0.77
     yourselves
    0.73
     those
    0.69
     yourself
    0.68
     this
    0.66
     Jav
    0.65
     ourselves
    0.64
    Activations Density 0.064%

    No Known Activations