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. 10129
    Prev
    Next
    INDEX
    Explanations

    phrases related to events in a festival setting

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "od" and its variations in different 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
     shorth
    -0.68
     silence
    -0.67
     Ago
    -0.65
     Polo
    -0.65
     Leone
    -0.64
     Citadel
    -0.63
     Tempest
    -0.63
     Heist
    -0.61
     Goat
    -0.61
     Curiosity
    -0.60
    POSITIVE LOGITS
    yssey
    1.18
    odon
    1.10
    iamond
    1.09
    wig
    1.05
    opter
    1.03
    amn
    1.02
    od
    1.01
    ata
    1.00
    unn
    0.99
    emo
    0.99
    Activations Density 0.012%

    No Known Activations