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. 21539
    Prev
    Next
    INDEX
    Explanations

    terms indicating expiration or something coming to an end

    oai_token-act-pair · gpt-3.5-turbo

    terms related to expiration or the end of validity

    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
    urally
    -0.69
    ord
    -0.66
     interf
    -0.63
     Misty
    -0.62
     Main
    -0.62
    arch
    -0.62
    nz
    -0.61
    isky
    -0.61
     Traditional
    -0.60
     Lia
    -0.59
    POSITIVE LOGITS
     expire
    4.20
     expires
    3.25
     expired
    2.69
     expiration
    2.42
     lapse
    1.51
     renewal
    1.21
     renew
    1.10
     revoked
    1.09
     sunset
    1.07
     timeout
    1.06
    Activations Density 0.023%

    No Known Activations