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. 6-RES-JB
    6. 14305
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    statements about political processes and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orescent
    -0.62
    osion
    -0.58
     slee
    -0.57
     1886
    -0.57
    draw
    -0.56
     Binding
    -0.54
    ricks
    -0.54
    ipolar
    -0.54
    rush
    -0.54
    mix
    -0.54
    POSITIVE LOGITS
     merely
    0.83
    mere
    0.79
    NetMessage
    0.69
     simply
    0.68
    Rather
    0.65
    hub
    0.65
    amiya
    0.63
    Instead
    0.63
    PE
    0.62
    INESS
    0.61
    Activations Density 0.538%

    No Known Activations