© 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. 4159
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical recovery or improvement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to recovery processes

    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
    chery
    -0.68
    nic
    -0.68
    sky
    -0.67
    OPA
    -0.66
    colo
    -0.61
    chie
    -0.60
    à¨
    -0.59
    ãģ®æ
    -0.57
    fer
    -0.56
    VP
    -0.55
    POSITIVE LOGITS
    overy
    0.82
    ilitating
    0.79
    owship
    0.78
    aining
    0.77
    ees
    0.75
    chwitz
    0.74
    ains
    0.74
     recovered
    0.73
    ency
    0.72
    ability
    0.70
    Activations Density 0.046%

    No Known Activations