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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7060
    Prev
    Next
    INDEX
    Explanations

    words related to popular or well-known brands or products

    oai_token-act-pair · gpt-3.5-turbo

    references to "Hot" as it appears in various contexts, particularly related to rankings and popularity

    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
    ittal
    -0.74
     anesthesia
    -0.68
    theless
    -0.67
     muster
    -0.67
     stomach
    -0.66
     agon
    -0.66
    terday
    -0.66
     ess
    -0.65
     ble
    -0.65
     unab
    -0.63
    POSITIVE LOGITS
    mail
    1.07
    shots
    1.03
     Sauce
    1.02
    els
    1.01
    line
    0.97
     Deals
    0.95
    shot
    0.93
    Spot
    0.93
     Topic
    0.92
     Shots
    0.92
    Activations Density 0.033%

    No Known Activations