© 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. 9-RES-JB
    11. 9959
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to definitions or explanations

    oai_token-act-pair · gpt-3.5-turbo

    formal definitions and explanations of concepts

    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
    daq
    -0.80
     Guerrero
    -0.69
    DAQ
    -0.69
     Hitman
    -0.68
     Jagu
    -0.67
     Trident
    -0.67
    soDeliveryDate
    -0.66
    6666
    -0.65
    Champ
    -0.64
     Champ
    -0.64
    POSITIVE LOGITS
     intentional
    0.85
    lihood
    0.82
     grouping
    0.79
     behaviours
    0.79
     adherent
    0.78
     conduct
    0.77
     inability
    0.76
     act
    0.76
     knowingly
    0.75
     combining
    0.75
    Activations Density 0.381%

    No Known Activations