© 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. 16374
    Prev
    Next
    INDEX
    Explanations

    phrases related to causes or reasons

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate causation or conditions

    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
    nels
    -0.74
    anooga
    -0.71
    vier
    -0.69
    readable
    -0.66
    boxes
    -0.65
    ivas
    -0.64
    ickr
    -0.64
    Reviewed
    -0.63
    boats
    -0.63
    incinn
    -0.62
    POSITIVE LOGITS
     exhaustion
    0.73
     sheer
    0.69
     clot
    0.66
    GMT
    0.65
     variance
    0.64
     compensate
    0.64
    othy
    0.63
     witness
    0.62
    capacity
    0.62
     ensure
    0.61
    Activations Density 0.173%

    No Known Activations