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. 4-RES-JB
    6. 3373
    Prev
    Next
    INDEX
    Explanations

    words related to technology and settings/settings configurations

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms

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

    No Comments

    Negative Logits
    ¿½
    -0.72
    uckland
    -0.72
    SpaceEngineers
    -0.71
    theless
    -0.70
     fung
    -0.68
     mould
    -0.66
    */(
    -0.65
     concess
    -0.64
     numbering
    -0.63
     disapp
    -0.63
    POSITIVE LOGITS
    helm
    0.82
    ngth
    0.81
    alian
    0.71
    osterone
    0.68
    alia
    0.68
    intestinal
    0.68
    uve
    0.66
    ateg
    0.65
    oday
    0.64
    herer
    0.64
    Activations Density 0.278%

    No Known Activations