© 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. 3-RES-JB
    11. 22950
    Prev
    Next
    INDEX
    Explanations

    words related to difficult tasks or problems

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "challenge" in various contexts

    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
    ahon
    -0.75
    miah
    -0.69
     GEAR
    -0.69
    arbon
    -0.64
     Leaves
    -0.63
    riter
    -0.62
    otide
    -0.62
     Instrument
    -0.61
    reen
    -0.61
    ight
    -0.59
    POSITIVE LOGITS
     challenge
    0.95
    enged
    0.95
    chall
    0.85
    ioned
    0.82
    naires
    0.81
    Chall
    0.78
     posed
    0.78
    enges
    0.76
    staking
    0.75
     challenging
    0.74
    Activations Density 0.021%

    No Known Activations