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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 8229
    Prev
    Next
    INDEX
    Explanations

    unintelligible characters interspersed with occasional words

    oai_token-act-pair · gpt-3.5-turbo

    financial terms and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sembly
    -1.06
    eatures
    -0.92
     pse
    -0.90
    undai
    -0.90
     agre
    -0.88
     contrace
    -0.84
     exha
    -0.83
     oun
    -0.82
    etheless
    -0.81
     confir
    -0.79
    POSITIVE LOGITS
    ç
    1.62
    é
    1.62
    æ
    1.59
    å¸
    1.56
    åº
    1.56
    è
    1.56
    å
    1.56
    çļĦ
    1.53
    åĪ
    1.51
    åĬ
    1.51
    Activations Density 0.042%

    No Known Activations