© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 13851
    Prev
    Next
    INDEX
    Explanations

    mentioned issues and problems in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to operational problems and shortcomings

    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
    erenn
    -0.76
    amous
    -0.76
    Terror
    -0.74
    ombies
    -0.72
    ombie
    -0.72
    riots
    -0.70
    augh
    -0.69
    idal
    -0.69
    bern
    -0.69
    forts
    -0.68
    POSITIVE LOGITS
     wiring
    1.04
     handling
    1.02
     processing
    0.92
     rollout
    0.89
     interpreting
    0.88
     calibration
    0.87
     pacing
    0.87
     transmission
    0.84
     communication
    0.83
     ventilation
    0.83
    Activations Density 0.318%

    No Known Activations