© 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. 1736
    Prev
    Next
    INDEX
    Explanations

    adjectives describing size or quality

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that express descriptions or qualities

    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
    iphate
    -0.73
    othal
    -0.70
    ioxide
    -0.68
    aminer
    -0.68
     Ratt
    -0.66
    ript
    -0.64
     Shore
    -0.63
    LEASE
    -0.63
    ynthesis
    -0.62
    RPG
    -0.62
    POSITIVE LOGITS
    etheless
    1.06
     amounts
    1.04
    ly
    1.02
     enough
    0.98
     ones
    0.97
     quantities
    0.92
     observers
    0.89
    nesses
    0.89
    ially
    0.88
     versions
    0.85
    Activations Density 0.492%

    No Known Activations