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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10-RES-JB
    6. 20090
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or strong belief

    oai_token-act-pair · gpt-3.5-turbo

    conversational phrases expressing opinions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İĭ
    -0.76
    ership
    -0.73
     Presence
    -0.70
    é¾įå¥ij士
    -0.70
    Contents
    -0.69
    assembly
    -0.65
    -+-+
    -0.63
    Rated
    -0.63
     Assist
    -0.62
    ãĤ¢ãĥ«
    -0.62
    POSITIVE LOGITS
     forgot
    0.95
     sounds
    0.81
     sounded
    0.80
     kinda
    0.79
     sucks
    0.78
     kidding
    0.78
     spelled
    0.75
     fooled
    0.75
     tricked
    0.71
     got
    0.71
    Activations Density 0.223%

    No Known Activations