© 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. 12427
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes or actions taken, such as withdrawal, cancellation, and removal

    oai_token-act-pair · gpt-3.5-turbo

    terms related to actions of withdrawal, cancellation, or removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Fit
    -0.71
    rics
    -0.71
    rouse
    -0.65
    idth
    -0.64
    ivities
    -0.64
    eds
    -0.61
    iour
    -0.61
    ses
    -0.59
    iew
    -0.59
    Capture
    -0.56
    POSITIVE LOGITS
     by
    0.88
     altogether
    0.84
     unanimously
    0.80
     entirely
    0.80
    uled
    0.75
     abruptly
    0.74
     indefinitely
    0.73
    sole
    0.73
     aback
    0.70
     administr
    0.70
    Activations Density 0.142%

    No Known Activations