© 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. 14790
    Prev
    Next
    INDEX
    Explanations

    a variety of situations or conditions that span a range or spectrum

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate variation or range among topics or conditions

    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
    rics
    -0.71
    driving
    -0.70
    bis
    -0.69
    idity
    -0.63
    士
    -0.58
    iquette
    -0.58
    jug
    -0.58
    talk
    -0.57
    IV
    -0.57
     Submission
    -0.56
    POSITIVE LOGITS
     ranging
    1.06
    ranging
    0.95
    ĸļ
    0.91
     between
    0.88
    Ĥª
    0.79
     wildly
    0.76
     upwards
    0.74
    efully
    0.74
    between
    0.73
     across
    0.73
    Activations Density 0.039%

    No Known Activations