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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 3676
    Prev
    Next
    INDEX
    Explanations

    numerical values

    oai_token-act-pair · gpt-3.5-turbo

    specific numeric or promotional references and mentions within documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tumble
    -0.58
     stroll
    -0.57
     Canaver
    -0.57
     duplication
    -0.57
     downfall
    -0.57
     commute
    -0.56
     surn
    -0.55
     poop
    -0.51
     collisions
    -0.51
     anonymity
    -0.51
    POSITIVE LOGITS
    ause
    0.79
    oren
    0.71
    icken
    0.67
    etermined
    0.65
    yond
    0.63
    renheit
    0.63
    ene
    0.62
    owship
    0.62
    lass
    0.61
    sworth
    0.60
    Activations Density 0.902%

    No Known Activations