© 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. 7-RES-JB
    11. 20780
    Prev
    Next
    INDEX
    Explanations

    mentions of the physical geographic feature "Andes mountains."

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "ino" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesday
    -1.05
    lished
    -0.86
    chool
    -0.81
     Asgard
    -0.81
    ĸļ
    -0.78
    owship
    -0.76
    matically
    -0.73
    adr
    -0.72
    sworth
    -0.72
    mable
    -0.71
    POSITIVE LOGITS
    zzi
    0.99
    ero
    0.97
    etti
    0.93
    opsis
    0.90
     Rossi
    0.87
    ctions
    0.85
    chi
    0.84
    eno
    0.81
    zo
    0.80
    xit
    0.77
    Activations Density 0.027%

    No Known Activations