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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    6. 404
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Project" followed by a non-zero activation value

    oai_token-act-pair · gpt-3.5-turbo

    references to specific projects

    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
    aws
    -0.76
    gger
    -0.73
    combe
    -0.73
    Interstitial
    -0.67
    taboola
    -0.66
     nerv
    -0.64
    ãģĦ
    -0.63
    bane
    -0.62
    ously
    -0.62
    wa
    -0.62
    POSITIVE LOGITS
     Gutenberg
    1.55
    ion
    1.14
    ions
    1.08
    ioned
    0.96
    ors
    0.95
    eur
    0.87
    ile
    0.82
    ional
    0.79
    ually
    0.78
    iles
    0.78
    Activations Density 0.032%

    No Known Activations