© 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. 19546
    Prev
    Next
    INDEX
    Explanations

    words related to the animal "koala"

    oai_token-act-pair · gpt-3.5-turbo

    references to koalas and related geographical or legislative contexts

    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
    ingen
    -0.83
    Ax
    -0.82
    Hung
    -0.79
    Die
    -0.75
    Nap
    -0.73
    nings
    -0.72
    boards
    -0.71
    boarding
    -0.70
    cia
    -0.70
    Wolf
    -0.68
    POSITIVE LOGITS
    ensis
    0.92
    abama
    0.81
     valley
    0.80
    fortunately
    0.76
    onga
    0.76
    cffffcc
    0.76
    omorph
    0.73
     NSW
    0.71
     tigers
    0.69
     tract
    0.67
    Activations Density 0.011%

    No Known Activations