© 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 EvalsExportsinterp-engineNEWAPI 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. 16031
    Prev
    Next
    INDEX
    Explanations

    terms related to comparisons and evaluations

    oai_token-act-pair · gpt-3.5-turbo

    references to benchmarks and benchmarking processes

    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
    agan
    -0.86
    gren
    -0.77
    oho
    -0.75
    aina
    -0.75
    olia
    -0.74
    frey
    -0.72
    idan
    -0.71
    Else
    -0.71
    win
    -0.70
    kn
    -0.69
    POSITIVE LOGITS
     benchmark
    1.16
     benchmarks
    1.13
    marks
    0.87
     guiActiveUnfocused
    0.78
    mark
    0.76
    imony
    0.73
     indices
    0.72
     scores
    0.69
    bench
    0.69
    APH
    0.68
    Activations Density 0.010%

    No Known Activations