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. 7-RES-JB
    6. 22100
    Prev
    Next
    INDEX
    Explanations

    words related to rates and densities

    oai_token-act-pair · gpt-3.5-turbo

    various statistical measures related to population and rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pic
    -0.71
    icus
    -0.67
    Plug
    -0.66
    ãĤ±
    -0.65
    Lear
    -0.60
    itional
    -0.60
    ãĥĥãĥĪ
    -0.60
     Assignment
    -0.59
    ignant
    -0.59
    ergy
    -0.58
    POSITIVE LOGITS
     (<
    0.86
     (>
    0.85
    jri
    0.81
     coupled
    0.76
     compared
    0.74
     dur
    0.70
    elsius
    0.69
     (âĪĴ
    0.67
     due
    0.65
     (~
    0.63
    Activations Density 0.376%

    No Known Activations