© 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. 0-RES-JB
    11. 9934
    Prev
    Next
    INDEX
    Explanations

    phrases related to a small quantity or number of something

    oai_token-act-pair · gpt-3.5-turbo

    references to a small number or quantity of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ian
    -0.67
     caused
    -0.63
    anto
    -0.61
     Operation
    -0.60
    Finish
    -0.60
    iber
    -0.59
     induced
    -0.58
    TM
    -0.58
     payable
    -0.58
    ae
    -0.58
    POSITIVE LOGITS
     handful
    3.19
     dozen
    1.83
    dozen
    1.64
     few
    1.59
     bunch
    1.38
     plethora
    1.26
    few
    1.20
     couple
    1.18
     multitude
    1.14
     slew
    1.12
    Activations Density 0.020%

    No Known Activations