© 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. 1934
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative consequences or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating outcomes or consequences

    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
    hid
    -0.67
     doubtless
    -0.60
     Doodle
    -0.58
     THREE
    -0.58
     sandwic
    -0.58
     assorted
    -0.57
    Origin
    -0.56
    pes
    -0.56
     aliases
    -0.56
    bryce
    -0.55
    POSITIVE LOGITS
     anymore
    1.21
     meaningful
    1.12
     satisfactory
    1.04
     sufficient
    1.04
    acea
    1.02
     lasting
    1.00
     adequate
    0.98
     anything
    0.95
     substantive
    0.93
     any
    0.92
    Activations Density 0.672%

    No Known Activations