Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7576
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a choice or alternative

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate alternatives or choices

    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
    then
    -0.86
    ocracy
    -0.78
    NOW
    -0.76
    ires
    -0.72
    eth
    -0.69
    erest
    -0.67
    english
    -0.64
    our
    -0.62
    ETS
    -0.62
    now
    -0.61
    POSITIVE LOGITS
    ifice
    1.44
    chard
    1.43
    nam
    1.43
    acle
    1.42
    acles
    1.37
    chid
    1.35
     alternatively
    1.25
     otherwise
    1.24
    GAN
    1.17
    Else
    1.11
    Activations Density 0.169%

    No Known Activations