© 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. 20876
    Prev
    Next
    INDEX
    Explanations

    negative and critical phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or conditionality

    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
     Address
    -0.75
     address
    -0.74
     Division
    -0.74
     margin
    -0.71
     rotor
    -0.71
     avenue
    -0.71
     entry
    -0.70
     Tier
    -0.69
     Union
    -0.69
     ratification
    -0.69
    POSITIVE LOGITS
    your
    1.43
    same
    1.37
    every
    1.36
    shit
    1.32
    everything
    1.32
    another
    1.29
    enough
    1.27
    the
    1.27
    anything
    1.26
    nature
    1.25
    Activations Density 0.097%

    No Known Activations