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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-RES-JB
    6. 6966
    Prev
    Next
    INDEX
    Explanations

    references to legal cases involving criminal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of numerical data or statistics related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    entimes
    -0.79
    ESE
    -0.66
    mbuds
    -0.65
    ciating
    -0.61
    ======
    -0.61
    stuff
    -0.61
    hare
    -0.60
    worldly
    -0.60
    forth
    -0.60
    bill
    -0.59
    POSITIVE LOGITS
     pleaded
    0.76
     died
    0.76
     who
    0.76
     of
    0.74
     whose
    0.72
     suffered
    0.69
     suffers
    0.68
     grandson
    0.65
     grew
    0.65
     surrendered
    0.64
    Activations Density 0.090%

    No Known Activations