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. 15787
    Prev
    Next
    INDEX
    Explanations

    the name "Conn" with varying activations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Conn" or related references

    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
     Bulgar
    -0.80
    BALL
    -0.69
     simul
    -0.67
     civ
    -0.66
    doms
    -0.65
     metals
    -0.65
     Uzbek
    -0.65
    leased
    -0.63
    DragonMagazine
    -0.63
     materials
    -0.61
    POSITIVE LOGITS
    olly
    1.17
    elly
    1.14
    aught
    1.07
    acht
    1.02
    ivity
    0.99
    ider
    0.91
    isco
    0.88
     Smy
    0.85
     Conn
    0.84
    icol
    0.83
    Activations Density 0.019%

    No Known Activations