© 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. 4-RES-JB
    11. 10055
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempting without success

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to availability or lack thereof

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

    No Comments

    Negative Logits
    eric
    -0.72
     coron
    -0.67
     Inher
    -0.64
    mac
    -0.64
     Columb
    -0.64
     Patriarch
    -0.62
     OCD
    -0.59
     Nose
    -0.59
     Nicaragua
    -0.58
     Prin
    -0.58
    POSITIVE LOGITS
     avail
    1.13
    abilities
    1.04
    ĸļ
    1.02
     mathemat
    0.96
    awaru
    0.89
    ifully
    0.83
    prise
    0.82
    urations
    0.82
    ilege
    0.81
    ume
    0.80
    Activations Density 0.011%

    No Known Activations