© 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. 15808
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and courtroom settings

    oai_token-act-pair · gpt-3.5-turbo

    references to fame or recognition in various contexts

    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
     capacitor
    -0.56
     loader
    -0.53
     instead
    -0.53
     launcher
    -0.51
     interchange
    -0.50
     ideally
    -0.50
     resistor
    -0.50
     Simpl
    -0.50
     converted
    -0.49
     nanop
    -0.49
    POSITIVE LOGITS
     endeavors
    0.69
    thood
    0.68
    pieces
    0.67
     events
    0.67
     tragedies
    0.66
    events
    0.66
     activities
    0.66
     outings
    0.65
     agendas
    0.65
     successes
    0.65
    Activations Density 1.034%

    No Known Activations