© 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
    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. 5269
    Prev
    Next
    INDEX
    Explanations

    words related to technology, such as technical commands and details, and specific company names

    oai_token-act-pair · gpt-3.5-turbo

    entities or terms related to news articles or information updates

    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
     sinners
    -0.53
     ghetto
    -0.48
     mischief
    -0.47
     proto
    -0.47
     lousy
    -0.47
     witchcraft
    -0.46
     ruining
    -0.46
     mayhem
    -0.46
     crotch
    -0.46
     killers
    -0.46
    POSITIVE LOGITS
    atform
    0.55
    TAG
    0.52
    hiro
    0.51
    raq
    0.51
    lement
    0.50
    rik
    0.50
    hra
    0.50
    neau
    0.49
    aml
    0.48
    liam
    0.48
    Activations Density 2.415%

    No Known Activations