© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 22808
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the nature of challenges or difficulties

    oai_token-act-pair · gpt-3.5-turbo

    distinct sequences or terms that indicate hidden or underlying issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocular
    -0.66
     Hodg
    -0.62
    DCS
    -0.60
     Enlight
    -0.59
     Luxem
    -0.58
     Britann
    -0.58
    ption
    -0.58
    ãĥŁ
    -0.58
    selves
    -0.57
     Dresden
    -0.57
    POSITIVE LOGITS
    y
    2.63
    yk
    1.56
    ily
    1.53
    iness
    1.48
    iest
    1.47
    yz
    1.39
    yg
    1.38
    eenth
    1.35
    yles
    1.32
    ym
    1.30
    Activations Density 0.189%

    No Known Activations