© 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. 8-RES-JB
    11. 17755
    Prev
    Next
    INDEX
    Explanations

    words associated with medical treatment

    oai_token-act-pair · gpt-3.5-turbo

    repeated syllables or phonetic patterns in words

    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
    lain
    -0.69
     HH
    -0.69
    icles
    -0.62
     deterrence
    -0.58
    manship
    -0.58
     innocence
    -0.57
     confir
    -0.57
    umbn
    -0.57
    igators
    -0.56
     sovereignty
    -0.56
    POSITIVE LOGITS
    zzi
    1.32
    zzle
    1.24
    ffee
    1.18
    ppe
    1.15
    ven
    1.13
    ffe
    1.11
    pping
    1.10
    ppa
    1.08
    pp
    1.07
    pper
    1.07
    Activations Density 0.140%

    No Known Activations