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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 24015
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the word "Koch"

    oai_token-act-pair · gpt-3.5-turbo

    the recurring mention of the name "Och."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lettuce
    -0.66
     trailers
    -0.66
     racks
    -0.65
     reb
    -0.63
     Reno
    -0.63
     Ryder
    -0.63
     RE
    -0.63
     Rip
    -0.63
     halfway
    -0.63
     clips
    -0.62
    POSITIVE LOGITS
    och
    4.57
    oj
    1.21
    oche
    1.21
    oen
    1.21
    oka
    1.17
    uch
    1.16
    oc
    1.15
    oco
    1.13
    ok
    1.13
    ich
    1.12
    Activations Density 0.022%

    No Known Activations