© 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 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. 7-RES-JB
    11. 11020
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or decisions taken by individuals

    oai_token-act-pair · gpt-3.5-turbo

    actions related to participation and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.82
     reluct
    -0.80
    zsche
    -0.77
    iscons
    -0.71
    hy
    -0.68
    asking
    -0.68
    isoft
    -0.68
    rison
    -0.66
    hatt
    -0.64
    berus
    -0.64
    POSITIVE LOGITS
     themselves
    0.68
    meric
    0.65
     PHI
    0.63
     regularly
    0.63
     Peg
    0.59
     Phi
    0.59
    animate
    0.59
     cellul
    0.59
     genetically
    0.59
    able
    0.57
    Activations Density 0.217%

    No Known Activations