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. 8-RES-JB
    6. 3741
    Prev
    Next
    INDEX
    Explanations

    date and time references

    oai_token-act-pair · gpt-3.5-turbo

    various elements related to dates, times, or specific identifiers in textual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.78
    Reloaded
    -0.66
    Wisconsin
    -0.65
     Gleaming
    -0.60
     aggregation
    -0.60
    ``
    -0.58
    KNOWN
    -0.58
    isode
    -0.57
    });
    -0.56
    ascular
    -0.56
    POSITIVE LOGITS
    lang
    0.72
    si
    0.71
     Quan
    0.67
     XL
    0.64
    dn
    0.63
    cription
    0.63
    esi
    0.62
    xual
    0.62
    rin
    0.62
    tch
    0.62
    Activations Density 0.553%

    No Known Activations