© 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. 2-RES-JB
    11. 7058
    Prev
    Next
    INDEX
    Explanations

    questions

    oai_token-act-pair · gpt-3.5-turbo

    questions beginning with "What."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roads
    -0.71
     seas
    -0.67
     steril
    -0.65
    rop
    -0.63
    gal
    -0.61
    ped
    -0.61
     op
    -0.60
    por
    -0.59
    trop
    -0.59
     indoors
    -0.59
    POSITIVE LOGITS
    soever
    1.28
     happens
    0.97
     Lies
    0.89
     distinguishes
    0.85
     happ
    0.85
     happened
    0.83
     Happ
    0.82
    nces
    0.77
     kinds
    0.77
     Makes
    0.74
    Activations Density 0.049%

    No Known Activations