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. 0-RES-JB
    6. 22934
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "publish" or its variants

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "publish" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overhe
    -0.63
     crystal
    -0.61
     prev
    -0.61
     overall
    -0.61
     gearing
    -0.60
     crystals
    -0.60
     matrix
    -0.59
     proxy
    -0.59
     equival
    -0.58
     concent
    -0.58
    POSITIVE LOGITS
    lish
    4.86
    lishing
    2.12
    lishes
    1.82
    lished
    1.58
    lisher
    1.40
    lez
    1.20
    rious
    1.03
    lyak
    1.02
    bish
    0.99
    leness
    0.96
    Activations Density 0.013%

    No Known Activations