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. 6-RES-JB
    6. 22461
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs indicating physical conditions or states of being

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various physical and emotional conditions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hops
    -1.00
    hots
    -0.94
    lees
    -0.94
    stories
    -0.92
    ometers
    -0.90
    ships
    -0.85
    assies
    -0.84
    events
    -0.83
    zees
    -0.82
    tracks
    -0.82
    POSITIVE LOGITS
     version
    0.82
     array
    0.81
     occurrence
    0.79
     example
    0.78
     bunch
    0.78
     chunk
    0.75
     lineup
    0.75
     assortment
    0.75
     figure
    0.74
     portion
    0.73
    Activations Density 0.206%

    No Known Activations