© 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. 3109
    Prev
    Next
    INDEX
    Explanations

    positive evaluations and recommendations

    oai_token-act-pair · gpt-3.5-turbo

    statements of opinion or evaluation about various subjects

    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
    urry
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    orsi
    -0.69
    ioned
    -0.67
     Cosponsors
    -0.67
    è¦ļéĨĴ
    -0.66
    encies
    -0.64
    indu
    -0.62
     Consult
    -0.62
    udeau
    -0.62
    POSITIVE LOGITS
     definitely
    1.37
     undeniably
    1.32
     downright
    1.27
     awesome
    1.25
     fantastic
    1.23
     terrific
    1.20
     certainly
    1.19
     gorgeous
    1.19
     delightful
    1.17
     priceless
    1.17
    Activations Density 0.319%

    No Known Activations