© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4785
    Prev
    Next
    INDEX
    Explanations

    mentions of things related to parity or similarity

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'par' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osures
    -0.75
     Dynamo
    -0.75
    ngth
    -0.73
     Shiny
    -0.70
    ãĤ£
    -0.69
    gemony
    -0.68
    icity
    -0.68
    ignty
    -0.66
     Zh
    -0.66
     Cain
    -0.66
    POSITIVE LOGITS
     par
    3.82
    par
    2.06
     Par
    2.05
    Par
    1.82
     PAR
    1.42
     para
    1.35
    PAR
    1.30
     pars
    1.16
     parade
    1.08
     paras
    1.07
    Activations Density 0.010%

    No Known Activations