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. 1-RES-JB
    6. 19546
    Prev
    Next
    INDEX
    Explanations

    phrases related to competition or comparison

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "match."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.94
    irtual
    -0.82
    aug
    -0.71
    umn
    -0.68
    cember
    -0.67
    raq
    -0.66
     Alz
    -0.65
    pez
    -0.64
    ################################
    -0.63
    sie
    -0.63
    POSITIVE LOGITS
     match
    1.22
     matches
    1.17
    match
    1.07
     Match
    1.02
     matched
    0.91
    Match
    0.90
    maker
    0.85
    makers
    0.81
    ees
    0.80
    making
    0.80
    Activations Density 0.014%

    No Known Activations