© 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. 15617
    Prev
    Next
    INDEX
    Explanations

    phrases related to possession or control

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with concepts of control and governance

    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
     redacted
    -0.62
     candid
    -0.62
    vasive
    -0.59
    livious
    -0.58
     admitting
    -0.57
     Invalid
    -0.56
     Rhod
    -0.54
    ipolar
    -0.53
    accompanied
    -0.53
     Missing
    -0.52
    POSITIVE LOGITS
    asses
    0.84
    vre
    0.84
    aces
    0.78
    adle
    0.74
    insula
    0.72
    irements
    0.72
    igree
    0.71
    rils
    0.70
    ills
    0.69
    elight
    0.68
    Activations Density 0.266%

    No Known Activations