© 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. 20064
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or the need for explanations

    oai_token-act-pair · gpt-3.5-turbo

    references to situations or objects followed by the words "that" or "this."

    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
    istries
    -0.90
    itatively
    -0.84
    ãĤ¹ãĥĪ
    -0.81
    izens
    -0.81
    acements
    -0.79
    endez
    -0.78
    amia
    -0.78
    izont
    -0.77
    aciously
    -0.77
    enegger
    -0.77
    POSITIVE LOGITS
     happens
    1.46
     happened
    1.36
     occurs
    1.33
     occurred
    1.17
     transpired
    1.01
     applies
    1.00
     happen
    0.97
     tactic
    0.96
     translates
    0.96
     phenomenon
    0.94
    Activations Density 0.190%

    No Known Activations