© 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. 10-RES-JB
    11. 3217
    Prev
    Next
    INDEX
    Explanations

    instances of people meeting or interacting with each other

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "met" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.71
    vernment
    -0.68
    wards
    -0.67
    otine
    -0.64
    cible
    -0.64
    creation
    -0.63
    anship
    -0.63
    pps
    -0.62
    eware
    -0.62
     nutshell
    -0.62
    POSITIVE LOGITS
    amorph
    1.36
    ioned
    0.99
    tle
    0.90
    ropolis
    0.89
    agame
    0.84
     with
    0.81
     privately
    0.79
    reon
    0.73
    ees
    0.71
    atars
    0.71
    Activations Density 0.052%

    No Known Activations