© 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. 22928
    Prev
    Next
    INDEX
    Explanations

    short phrases that are followed by a rhetorical question or a statement with emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating awareness or understanding of a situation

    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
    Ire
    -0.78
    aldi
    -0.72
    é¾įå
    -0.70
    nor
    -0.70
    ISA
    -0.67
    oes
    -0.66
    ophon
    -0.65
    Contents
    -0.64
    itals
    -0.64
    falls
    -0.64
    POSITIVE LOGITS
     kidding
    0.82
     yourselves
    0.81
     yourself
    0.70
     bored
    0.65
    ?!
    0.63
     drill
    0.62
     wanna
    0.61
     spoil
    0.59
     me
    0.58
     ya
    0.58
    Activations Density 0.182%

    No Known Activations