© 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. 0-RES-JB
    11. 15088
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to a person named Hardison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isode
    -0.69
    soDeliveryDate
    -0.68
    uebl
    -0.67
    illance
    -0.66
    opsis
    -0.65
     expression
    -0.63
     originated
    -0.60
    inois
    -0.60
     flame
    -0.59
     fa
    -0.59
    POSITIVE LOGITS
     Hard
    3.60
    Hard
    3.03
    hard
    2.17
     hard
    1.83
     Soft
    1.51
     Tough
    1.51
     Hardcore
    1.50
     harder
    1.45
     Easy
    1.44
     Impossible
    1.40
    Activations Density 0.011%

    No Known Activations