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. 10-RES-JB
    6. 19445
    Prev
    Next
    INDEX
    Explanations

    titles or references to job positions such as "managing director."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "managing" in various contexts

    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
    weed
    -0.83
    ascript
    -0.82
    behind
    -0.74
    iness
    -0.73
    osate
    -0.72
    earable
    -0.72
    cellence
    -0.72
    correct
    -0.71
     cheaply
    -0.71
     reacting
    -0.71
    POSITIVE LOGITS
     partner
    0.84
     Factors
    0.80
     member
    0.79
     factors
    0.75
     spouse
    0.74
     partners
    0.73
    iaries
    0.73
     factor
    0.72
     heights
    0.72
    ãĥŁ
    0.71
    Activations Density 0.134%

    No Known Activations