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. 10-RES-JB
    6. 4147
    Prev
    Next
    INDEX
    Explanations

    references to tape or tape-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to tape recordings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ationally
    -0.68
    å§«
    -0.63
    lein
    -0.63
    ancial
    -0.63
     philanthrop
    -0.61
    imov
    -0.60
     Alonso
    -0.60
     unpre
    -0.60
    abad
    -0.60
    Ĭ±
    -0.58
    POSITIVE LOGITS
     recorder
    1.21
     tapes
    1.01
     tape
    1.00
    red
    0.99
     Tape
    0.98
     cassette
    0.94
     recordings
    0.94
    clip
    0.88
    recorded
    0.87
     taped
    0.84
    Activations Density 0.028%

    No Known Activations