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. 11-RES-JB
    6. 16100
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Ker."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ker" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Unic
    -0.60
    UME
    -0.59
     billions
    -0.58
     harmless
    -0.57
     Hogan
    -0.55
     hundreds
    -0.55
    Quotes
    -0.55
    ãģ®éŃĶ
    -0.54
     thousands
    -0.54
     Pot
    -0.54
    POSITIVE LOGITS
    rigan
    1.35
    mit
    1.21
    bal
    1.12
    rison
    1.04
    ber
    1.03
    jriwal
    1.02
    usalem
    1.02
    imov
    0.98
    seys
    0.97
    berus
    0.97
    Activations Density 0.036%

    No Known Activations