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. 8519
    Prev
    Next
    INDEX
    Explanations

    words related to something coming to an end or reaching a time limit

    oai_token-act-pair · gpt-3.5-turbo

    terms related to expiration or the ending of validity periods

    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
    oward
    -0.73
    ier
    -0.71
    agame
    -0.64
    Physical
    -0.62
    dds
    -0.62
    oly
    -0.61
    bt
    -0.58
     Twe
    -0.58
    uss
    -0.58
     portray
    -0.58
    POSITIVE LOGITS
     expired
    3.96
     expires
    1.77
     expiration
    1.18
     deteriorated
    1.18
     stalled
    1.17
     faded
    1.13
     collapsed
    1.10
     revoked
    1.08
     aborted
    1.06
     dried
    1.05
    Activations Density 0.012%

    No Known Activations