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. 9-RES-JB
    6. 20594
    Prev
    Next
    INDEX
    Explanations

    phrases related to software

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating compatibility or suitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alan
    -0.78
     externalToEVAOnly
    -0.71
    adr
    -0.70
    soever
    -0.67
     suffice
    -0.66
    artifacts
    -0.66
    é¾
    -0.65
     lest
    -0.65
    ))))
    -0.64
    ouf
    -0.63
    POSITIVE LOGITS
     sale
    1.09
     beginners
    0.97
    ked
    0.91
    bidden
    0.89
     hire
    0.89
    aging
    0.88
     detecting
    0.87
    agers
    0.86
     iPad
    0.82
    geries
    0.82
    Activations Density 0.166%

    No Known Activations