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. 9097
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific word or concept, "Hammer", multiple times at various contexts

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to specific names and organizations

    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
     polyg
    -0.76
    yss
    -0.74
     coy
    -0.74
     CES
    -0.74
    LV
    -0.72
    rang
    -0.72
     prepaid
    -0.72
     hum
    -0.71
     pas
    -0.70
     vide
    -0.70
    POSITIVE LOGITS
     Hammer
    2.75
     DW
    1.85
     Kaiser
    1.41
     Slayer
    1.32
     Kirby
    1.30
     hammer
    1.21
     Penny
    1.21
     Slaughter
    1.16
     Baird
    1.12
     Defender
    1.09
    Activations Density 0.054%

    No Known Activations