© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1626
    Prev
    Next
    INDEX
    Explanations

    the word "one" at various activation levels

    oai_token-act-pair · gpt-3.5-turbo

    the word "one" used in various contexts and formations

    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
    inders
    -0.72
    ooks
    -0.68
    ographics
    -0.66
    ories
    -0.66
    photos
    -0.66
    ocal
    -0.65
    actionDate
    -0.64
    ulner
    -0.61
    akings
    -0.60
    umble
    -0.60
    POSITIVE LOGITS
     hundred
    0.98
     wonders
    0.98
     assumes
    0.97
     imag
    0.88
     Hundred
    0.85
     expects
    0.84
     thousand
    0.82
     learns
    0.81
     suspects
    0.80
     sided
    0.77
    Activations Density 0.120%

    No Known Activations