© 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. 7-RES-JB
    11. 2925
    Prev
    Next
    INDEX
    Explanations

    phrases related to batch processing

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruption
    -0.73
    ophers
    -0.70
    pose
    -0.70
     Commissioners
    -0.69
    peria
    -0.68
     poles
    -0.68
    PLIED
    -0.67
    plex
    -0.67
     stances
    -0.66
    gling
    -0.66
    POSITIVE LOGITS
     batches
    0.96
     batch
    0.92
    mates
    0.86
    meal
    0.74
     thereof
    0.70
    ting
    0.68
     sizes
    0.68
    arse
    0.67
    uling
    0.65
    arian
    0.65
    Activations Density 0.025%

    No Known Activations