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. 3-RES-JB
    6. 19795
    Prev
    Next
    INDEX
    Explanations

    words related to a specific piece of furniture - the bed

    oai_token-act-pair · gpt-3.5-turbo

    references to beds and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.90
    vernment
    -0.79
    auga
    -0.74
    İĭ
    -0.74
    rencies
    -0.68
    aminer
    -0.66
    ãĥ£
    -0.65
     Galile
    -0.62
    IJ
    -0.61
     doubtful
    -0.61
    POSITIVE LOGITS
    ding
    1.27
    room
    1.04
    ridden
    1.03
    ded
    1.02
    bed
    1.00
     mattress
    0.97
    stead
    0.93
    rock
    0.93
    bugs
    0.91
    lam
    0.89
    Activations Density 0.012%

    No Known Activations