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. 1230
    Prev
    Next
    INDEX
    Explanations

    specific names, likely related to characters or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to characters and places, particularly in a narrative context

    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
    tering
    -0.83
     Cumber
    -0.75
    zman
    -0.72
    eers
    -0.68
     Manip
    -0.67
    enburg
    -0.67
     Wonderland
    -0.64
    zel
    -0.64
     inval
    -0.64
     Box
    -0.64
    POSITIVE LOGITS
    phia
    0.95
    ourse
    0.81
    prise
    0.75
    icago
    0.72
    prises
    0.71
    ĺħ
    0.70
    roots
    0.69
    WP
    0.69
     Trace
    0.68
    dain
    0.68
    Activations Density 0.065%

    No Known Activations