© 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. 10-RES-JB
    11. 16659
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions or beliefs about different groups or ideologies

    oai_token-act-pair · gpt-3.5-turbo

    phrases that assert the existence or characteristics of groups or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WER
    -0.76
    mentioned
    -0.76
    urry
    -0.75
    stood
    -0.71
     Moines
    -0.70
    ESE
    -0.69
    sers
    -0.67
    rief
    -0.66
    noticed
    -0.66
     Adds
    -0.65
    POSITIVE LOGITS
     unfit
    1.20
     inherently
    1.17
     incapable
    1.16
     unworthy
    1.14
     illegitimate
    1.09
     somehow
    1.08
     intrinsically
    1.05
     insufficient
    1.05
     incompatible
    1.05
     conspiring
    1.04
    Activations Density 0.293%

    No Known Activations