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. 8-RES-JB
    6. 15877
    Prev
    Next
    INDEX
    Explanations

    the occurrence of specific phrases or sentences

    oai_token-act-pair · gpt-3.5-turbo

    common phrases and quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÄŁ
    -0.75
    fman
    -0.74
    llah
    -0.69
     appointments
    -0.69
     contrace
    -0.67
     hemor
    -0.67
    oÄŁ
    -0.66
    gur
    -0.63
     Thro
    -0.63
    ockets
    -0.63
    POSITIVE LOGITS
    phrase
    1.15
    ology
    1.04
     uttered
    1.03
     phrase
    0.92
     phrases
    0.89
     coined
    0.89
    terday
    0.84
    stress
    0.84
     slogan
    0.80
    stick
    0.77
    Activations Density 0.060%

    No Known Activations