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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8998
    Prev
    Next
    INDEX
    Explanations

    terms related to probability and chance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to probability and probabilistic concepts

    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
     palms
    -0.75
     Valhalla
    -0.70
     Hust
    -0.68
    OWN
    -0.64
    ideshow
    -0.62
     Peninsula
    -0.62
     Sparrow
    -0.61
     cheeks
    -0.59
     Valent
    -0.59
    overs
    -0.57
    POSITIVE LOGITS
    iotics
    1.36
    iotic
    1.27
    abil
    1.22
    osc
    1.10
    abilities
    0.96
    bably
    0.96
    imon
    0.95
    bly
    0.92
    orship
    0.91
    orate
    0.88
    Activations Density 0.043%

    No Known Activations