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. 6-RES-JB
    6. 21529
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizations, committees, and commissions

    oai_token-act-pair · gpt-3.5-turbo

    references to official organizations or institutions

    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
     peril
    -0.76
     ascend
    -0.75
     pageant
    -0.73
     legend
    -0.73
     lif
    -0.72
     whisper
    -0.71
     descend
    -0.71
     ascent
    -0.70
     row
    -0.70
     kittens
    -0.69
    POSITIVE LOGITS
     Against
    0.85
     Provision
    0.85
    Point
    0.84
     Registry
    0.79
     Programme
    0.75
     Room
    0.75
    Virtual
    0.75
     Of
    0.74
    Gas
    0.74
    Scope
    0.74
    Activations Density 0.141%

    No Known Activations