© 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. 9-RES-JB
    11. 2285
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate additional information or elements in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "well" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auri
    -0.71
    cair
    -0.64
    anos
    -0.63
    bley
    -0.63
    oret
    -0.61
    aldi
    -0.60
    ories
    -0.60
    emen
    -0.60
    mission
    -0.59
    ve
    -0.57
    POSITIVE LOGITS
     as
    1.03
     AS
    0.59
     known
    0.59
    nesses
    0.58
     evidenced
    0.55
    Parameters
    0.55
     occasional
    0.55
     suited
    0.54
    vertisement
    0.52
     headlined
    0.52
    Activations Density 0.030%

    No Known Activations