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. 10-RES-JB
    6. 20725
    Prev
    Next
    INDEX
    Explanations

    descriptions of technical changes and updates

    oai_token-act-pair · gpt-3.5-turbo

    terms related to changes and modifications, particularly in technology and design

    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
    arious
    -0.77
     Lust
    -0.68
    trace
    -0.65
    runtime
    -0.61
     Solo
    -0.59
     narrated
    -0.58
     Bees
    -0.58
    ruciating
    -0.58
     Interstellar
    -0.57
     Kart
    -0.57
    POSITIVE LOGITS
     changes
    2.10
     change
    2.00
     overhaul
    1.83
    Changes
    1.82
     reorgan
    1.78
     restructuring
    1.78
    changes
    1.75
     revisions
    1.73
     Changes
    1.71
     redesign
    1.71
    Activations Density 1.391%

    No Known Activations