© 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. 3-RES-JB
    11. 3652
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer programming and expertise/aptitude

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to aptitude and skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pall
    -0.76
    RFC
    -0.74
    EEE
    -0.73
    Ô
    -0.73
    plementation
    -0.71
     Sheep
    -0.67
    vernment
    -0.67
     PAN
    -0.65
    IRD
    -0.64
    @#&
    -0.64
    POSITIVE LOGITS
    itude
    1.65
    itudes
    1.30
    itud
    0.99
     apt
    0.94
    entimes
    0.89
    ties
    0.81
     recip
    0.77
     tem
    0.77
    ancy
    0.75
     suscept
    0.74
    Activations Density 0.008%

    No Known Activations