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. 22151
    Prev
    Next
    INDEX
    Explanations

    phrases related to removal or exclusion

    oai_token-act-pair · gpt-3.5-turbo

    concepts and instances of elimination

    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
    rium
    -0.70
    isters
    -0.69
    ETF
    -0.68
    embed
    -0.67
    fab
    -0.67
    dn
    -0.67
    felt
    -0.66
    ebus
    -0.64
    akening
    -0.64
    nan
    -0.64
    POSITIVE LOGITS
     altogether
    0.92
     duplication
    0.86
     needless
    0.77
     prejudice
    0.77
     redundancy
    0.76
     redund
    0.76
    aneous
    0.76
    istically
    0.70
     distractions
    0.70
     clutter
    0.69
    Activations Density 0.082%

    No Known Activations