© 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. 11568
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exceptions or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating flaws or limitations in a system or situation

    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
    ĸļ
    -1.05
    ynthesis
    -0.85
    abit
    -0.76
    orest
    -0.74
    ride
    -0.72
    thood
    -0.71
    hospital
    -0.71
    earch
    -0.71
    ondon
    -0.70
     Vide
    -0.70
    POSITIVE LOGITS
     flaws
    1.65
     caveats
    1.62
     drawbacks
    1.54
     shortcomings
    1.52
     pitfalls
    1.42
     inconsistencies
    1.42
     loopholes
    1.41
     glitches
    1.40
     limitations
    1.40
     complications
    1.39
    Activations Density 0.321%

    No Known Activations