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. 11411
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating an increase or growth in something over time

    oai_token-act-pair · gpt-3.5-turbo

    the conjunctions "and" and "or" in various contexts

    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
    ADVERTISEMENT
    -0.73
     robber
    -0.72
     Hacker
    -0.62
    GD
    -0.59
     robbery
    -0.59
    ATTLE
    -0.58
    RAW
    -0.58
    rawdownloadcloneembedreportprint
    -0.58
    CHAT
    -0.58
     doping
    -0.57
    POSITIVE LOGITS
    rogens
    0.74
    aturally
    0.70
    leans
    0.68
    vous
    0.66
    acho
    0.65
    hett
    0.64
    rogen
    0.63
    ween
    0.63
    leases
    0.62
    seek
    0.62
    Activations Density 0.068%

    No Known Activations