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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8522
    Prev
    Next
    INDEX
    Explanations

    contractions of 'is', 'has', and 'was'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the subject "it" and its actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luaj
    -0.77
    orsi
    -0.65
     ("
    -0.64
    bies
    -0.63
    andise
    -0.62
     looms
    -0.62
    edIn
    -0.61
    Versions
    -0.61
    asses
    -0.60
    era
    -0.59
    POSITIVE LOGITS
     definitely
    1.16
     gonna
    1.00
     gotta
    0.93
     defin
    0.91
     certainly
    0.91
     absolutely
    0.89
     basically
    0.89
     obviously
    0.88
     probably
    0.85
    initely
    0.83
    Activations Density 0.289%

    No Known Activations