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. 8-RES-JB
    6. 4346
    Prev
    Next
    INDEX
    Explanations

    the name "Ch" or "Ch9"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or entity named "Ch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lockout
    -0.68
    FORMATION
    -0.68
    WARD
    -0.67
     visitation
    -0.66
    INGTON
    -0.65
     Ajax
    -0.63
     constrained
    -0.62
     Trilogy
    -0.61
     "$:/
    -0.60
    ITED
    -0.60
    POSITIVE LOGITS
    amps
    1.24
    assis
    1.23
    unks
    1.22
    orus
    1.21
    ieft
    1.17
    ivalry
    1.17
    isel
    1.16
    angel
    1.15
    annels
    1.15
    owder
    1.14
    Activations Density 0.033%

    No Known Activations