© 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. 9-RES-JB
    11. 20840
    Prev
    Next
    INDEX
    Explanations

    phrases associated with personal beliefs or convictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating interpersonal relationships and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endiary
    -0.83
    interstitial
    -0.76
     prepar
    -0.76
    ancial
    -0.73
    urgical
    -0.72
    PDF
    -0.69
    everal
    -0.68
    earchers
    -0.68
    umerous
    -0.67
    urst
    -0.67
    POSITIVE LOGITS
     me
    1.56
     yourself
    1.51
     yourselves
    1.51
     him
    1.48
     myself
    1.33
     us
    1.31
     HIM
    1.29
     ya
    1.28
     somebody
    1.26
     thee
    1.25
    Activations Density 0.725%

    No Known Activations