© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 23851
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatments or substances

    oai_token-act-pair · gpt-3.5-turbo

    prefixes and suffixes commonly associated with specialized terms or concepts, particularly in scientific or socio-political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.92
     Revel
    -0.71
    gur
    -0.67
     Duck
    -0.64
     Parables
    -0.61
    taker
    -0.61
     laun
    -0.60
     Rabbit
    -0.60
     absent
    -0.60
     HIT
    -0.58
    POSITIVE LOGITS
    hedral
    1.33
    uthor
    1.24
    verse
    1.11
    ctr
    1.06
    operative
    1.06
    esthesia
    1.05
    vernment
    1.03
    ples
    1.03
    herence
    0.99
    cephal
    0.99
    Activations Density 0.196%

    No Known Activations