© 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. 4613
    Prev
    Next
    INDEX
    Explanations

    phrases related to the potential negative consequences of various scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate potential or possibility

    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
     bidding
    -0.65
     Quarter
    -0.62
     Mant
    -0.60
     Fighter
    -0.60
     Federation
    -0.59
     Fighting
    -0.58
     Prayer
    -0.57
     worsh
    -0.57
     Hamp
    -0.56
     submitting
    -0.56
    POSITIVE LOGITS
    't
    1.52
    adian
    1.07
    berra
    1.05
     confuse
    1.02
     easily
    1.01
    isters
    1.00
     complicate
    0.99
     be
    0.99
    NOT
    0.98
    ister
    0.96
    Activations Density 0.124%

    No Known Activations