© 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. 10-RES-JB
    11. 18904
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Given" used to introduce a condition or rationale

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "given," indicating the presence of conditions or considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scribe
    -0.93
    enium
    -0.74
    oola
    -0.73
    inating
    -0.73
    isode
    -0.72
    enf
    -0.72
    inates
    -0.71
    rouse
    -0.71
    odge
    -0.69
    ade
    -0.69
    POSITIVE LOGITS
     how
    1.21
     that
    0.91
     ample
    0.90
     what
    0.89
     recent
    0.87
     its
    0.84
     the
    0.82
     current
    0.81
     similarities
    0.79
     their
    0.79
    Activations Density 0.067%

    No Known Activations