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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 10834
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases emphasizing outcomes or results

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tesy
    -0.86
     teasp
    -0.83
     carbohyd
    -0.81
     zo
    -0.79
    yssey
    -0.77
    ::::::::
    -0.75
     gobl
    -0.73
     encount
    -0.72
     caster
    -0.72
     tracker
    -0.72
    POSITIVE LOGITS
     Hence
    1.33
     Indeed
    1.33
     Worse
    1.27
     Governments
    1.25
     Consequently
    1.25
     Thus
    1.25
     Moreover
    1.22
     Likewise
    1.22
     Few
    1.22
     Meanwhile
    1.21
    Activations Density 0.380%

    No Known Activations