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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23233
    Prev
    Next
    INDEX
    Explanations

    terms related to sports teams and competitions

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation "NT" related to a specific context or terminology

    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
    uras
    -0.69
     clos
    -0.63
     spouse
    -0.61
     month
    -0.61
     Valerie
    -0.60
     Valentine
    -0.60
     marches
    -0.60
     husband
    -0.59
     bay
    -0.59
     sab
    -0.59
    POSITIVE LOGITS
    NT
    4.63
     NT
    1.96
    nt
    1.75
    NS
    1.58
    ND
    1.39
    NG
    1.32
    NF
    1.28
    NK
    1.27
    NC
    1.24
    Ns
    1.23
    Activations Density 0.018%

    No Known Activations