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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 2995
    Prev
    Next
    INDEX
    Explanations

    mentions of footwear, particularly boots

    oai_token-act-pair · gpt-3.5-turbo

    mentions of boots

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.71
    udic
    -0.68
    ught
    -0.68
    Ĭ±
    -0.68
    enced
    -0.68
     NAD
    -0.67
    encers
    -0.67
     neurot
    -0.67
    LD
    -0.66
    kefeller
    -0.65
    POSITIVE LOGITS
    strap
    1.89
    loader
    1.14
    stra
    1.11
    legged
    1.03
    camp
    0.99
    leg
    0.88
    tails
    0.87
     loader
    0.83
    boot
    0.81
    lake
    0.81
    Activations Density 0.012%

    No Known Activations