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. 9-RES-JB
    6. 14616
    Prev
    Next
    INDEX
    Explanations

    verbs in the form "come to" followed by a verb or noun

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "come to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bilt
    -0.81
    neys
    -0.71
     Contributions
    -0.64
    vich
    -0.59
    croft
    -0.59
    resy
    -0.59
    gat
    -0.57
    VPN
    -0.57
    TION
    -0.56
    vP
    -0.56
    POSITIVE LOGITS
     fruition
    1.31
     prominence
    1.00
     haunt
    0.90
     shove
    0.88
     dominate
    0.81
     blows
    0.80
     grips
    0.80
     resemble
    0.77
    ilers
    0.75
     pass
    0.74
    Activations Density 0.050%

    No Known Activations