Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 2982
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements or units expressed in numerical form

    oai_token-act-pair · gpt-3.5-turbo

    quantitative measurements or counts related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exception
    -0.74
     bidder
    -0.64
     Canary
    -0.61
    ties
    -0.59
    rison
    -0.58
    rum
    -0.58
    nce
    -0.58
    ependent
    -0.58
     defe
    -0.57
    alter
    -0.57
    POSITIVE LOGITS
    poons
    1.40
     apiece
    1.36
     per
    1.17
    pace
    0.99
    paces
    0.97
    peed
    0.97
    pread
    0.97
     total
    0.95
    mith
    0.92
    hips
    0.87
    Activations Density 0.228%

    No Known Activations