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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 1935
    Prev
    Next
    INDEX
    Explanations

    phrases related to government policies or public affairs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships or associations

    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
    PDF
    -0.68
     Awakens
    -0.67
    orb
    -0.66
     Oo
    -0.64
    craft
    -0.63
    blogspot
    -0.63
    pdf
    -0.62
    jen
    -0.61
    olla
    -0.61
    orns
    -0.60
    POSITIVE LOGITS
    idth
    0.69
    blance
    0.64
     Chamberlain
    0.60
    EMBER
    0.60
    é¾įå¥ij士
    0.59
    vernment
    0.58
    ignty
    0.57
     sheer
    0.56
    Magikarp
    0.56
    ULE
    0.56
    Activations Density 0.538%

    No Known Activations