© 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. 2-RES-JB
    11. 11640
    Prev
    Next
    INDEX
    Explanations

    instances where an action is done or a state is described without a particular element or item

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "without" and its repeated usage in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oola
    -0.87
    mun
    -0.87
    raq
    -0.82
    omsky
    -0.76
    ulty
    -0.74
    mers
    -0.72
    des
    -0.69
    ocations
    -0.69
    cow
    -0.69
    ahime
    -0.69
    POSITIVE LOGITS
    lessly
    0.84
     knowing
    0.82
     blinking
    0.76
     sacrificing
    0.70
     mentioning
    0.70
     compromising
    0.69
     interruption
    0.69
     regard
    0.69
     substit
    0.69
     exception
    0.66
    Activations Density 0.038%

    No Known Activations