© 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. 5804
    Prev
    Next
    INDEX
    Explanations

    specific body parts or components related to machinery or geography

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific components or segments within various contexts

    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
    gently
    -0.71
     Situation
    -0.67
     Skies
    -0.67
    culosis
    -0.64
    anders
    -0.63
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.61
    pub
    -0.60
     Patron
    -0.60
    CHAT
    -0.60
    Recommend
    -0.59
    POSITIVE LOGITS
    meal
    0.92
    ridges
    0.88
     thereof
    0.84
    ridge
    0.79
    ials
    0.73
    heartedly
    0.70
    atum
    0.70
    etting
    0.68
    isans
    0.66
    lessly
    0.66
    Activations Density 0.037%

    No Known Activations