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. 23335
    Prev
    Next
    INDEX
    Explanations

    contractions of "is"

    oai_token-act-pair · gpt-3.5-turbo

    repeated uses of the contraction "he's" 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
    zes
    -0.66
    izes
    -0.65
    iew
    -0.63
    rence
    -0.60
    irm
    -0.60
    terior
    -0.60
    uple
    -0.60
     Result
    -0.59
    ization
    -0.58
    oint
    -0.58
    POSITIVE LOGITS
     gotta
    1.37
    been
    1.30
     gonna
    1.28
     been
    1.24
     got
    1.21
     gotten
    1.19
     gone
    0.94
     Been
    0.92
     supposed
    0.89
     going
    0.81
    Activations Density 0.080%

    No Known Activations