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. 0-RES-JB
    6. 2997
    Prev
    Next
    INDEX
    Explanations

    dates expressed in the format of four digits

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 2004

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cil
    -0.68
    zees
    -0.63
    ierre
    -0.63
    scl
    -0.62
     devils
    -0.62
    itu
    -0.62
     wand
    -0.59
    ilus
    -0.59
     Mn
    -0.59
     ste
    -0.59
    POSITIVE LOGITS
     2004
    2.83
    2004
    2.19
     2008
    1.91
     1996
    1.91
     1994
    1.88
     2006
    1.84
     1988
    1.84
     2003
    1.84
     1984
    1.82
     2002
    1.80
    Activations Density 0.040%

    No Known Activations