© 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. 10-RES-JB
    11. 10048
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or events within a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Back" 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
    ©¶æ¥µ
    -0.64
    ccess
    -0.63
    utical
    -0.63
    ihad
    -0.62
     Osc
    -0.62
     tyr
    -0.60
    izo
    -0.59
    isen
    -0.59
    ellen
    -0.59
     constitu
    -0.59
    POSITIVE LOGITS
    lash
    1.20
    stab
    1.18
    door
    1.11
    tracking
    1.08
    GROUND
    1.06
    yard
    1.05
    wards
    1.04
    stage
    1.04
    dated
    1.02
    pack
    1.02
    Activations Density 0.027%

    No Known Activations