© 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. 8-RES-JB
    11. 11372
    Prev
    Next
    INDEX
    Explanations

    names of individuals and places

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Men."

    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
    IVERS
    -0.64
    BLIC
    -0.63
     mono
    -0.63
    âĺħâĺħ
    -0.63
    VICE
    -0.62
    ITED
    -0.59
     chill
    -0.59
    ENC
    -0.58
     geo
    -0.58
    ENCY
    -0.58
    POSITIVE LOGITS
    endez
    1.41
    iscal
    1.18
    opausal
    1.14
    cius
    1.08
    uscript
    1.07
    aced
    1.05
    ager
    1.03
    orah
    1.01
    agogue
    1.01
    aces
    0.97
    Activations Density 0.035%

    No Known Activations