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. 8323
    Prev
    Next
    INDEX
    Explanations

    countries and entities separated by commas

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and coordinating phrases

    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
    ":"/
    -0.80
    agen
    -0.71
    conservancy
    -0.70
    çĭ
    -0.69
    WARE
    -0.69
    ibble
    -0.69
    BIP
    -0.68
    ULTS
    -0.64
    HB
    -0.63
    raught
    -0.63
    POSITIVE LOGITS
     etc
    1.17
     assorted
    1.10
    etc
    1.06
     others
    0.94
     possibly
    0.84
     other
    0.80
    rogens
    0.80
     ect
    0.72
     finally
    0.70
     subsequ
    0.69
    Activations Density 0.177%

    No Known Activations