© 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. 3-RES-JB
    11. 20433
    Prev
    Next
    INDEX
    Explanations

    references to beta versions or testing

    oai_token-act-pair · gpt-3.5-turbo

    references to beta testing software or applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AMI
    -0.87
    lli
    -0.86
    ĸļ
    -0.85
    advertisement
    -0.85
    aws
    -0.76
    say
    -0.76
    metics
    -0.75
    UAL
    -0.74
    aunder
    -0.73
    erva
    -0.72
    POSITIVE LOGITS
     beta
    1.00
     testers
    0.92
    beta
    0.88
     Beta
    0.88
    Beta
    0.83
     blocker
    0.82
     blockers
    0.77
     alpha
    0.77
     Centauri
    0.76
     release
    0.66
    Activations Density 0.009%

    No Known Activations