© 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. 19613
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'to' followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate hypothetical situations or conditional statements

    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
    Dur
    -0.70
    Ps
    -0.67
    padding
    -0.66
     Dur
    -0.66
     Bord
    -0.65
    FX
    -0.64
    Solid
    -0.62
     Bridges
    -0.61
    IOR
    -0.61
     Terr
    -0.61
    POSITIVE LOGITS
     succeed
    1.05
     choose
    0.98
     summarize
    0.98
     nominate
    0.96
     dedicate
    0.96
     decide
    0.93
     hypot
    0.93
     recreate
    0.92
     partake
    0.92
     stumble
    0.91
    Activations Density 0.048%

    No Known Activations