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. 11-RES-JB
    6. 15548
    Prev
    Next
    INDEX
    Explanations

    texts related to technical information or reports

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that provide examples or excerpts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    errors
    -0.80
    alties
    -0.79
    sbm
    -0.77
    andals
    -0.77
    brates
    -0.74
    aults
    -0.73
    artifacts
    -0.72
     Flavoring
    -0.71
    iencies
    -0.70
    icides
    -0.68
    POSITIVE LOGITS
     excerpt
    1.20
     rundown
    1.11
    ():
    1.03
     nutshell
    1.02
    :(
    1.02
    *:
    1.00
     snippet
    0.98
     kicker
    0.97
     synopsis
    0.97
     breakdown
    0.96
    Activations Density 0.184%

    No Known Activations