© 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. 18987
    Prev
    Next
    INDEX
    Explanations

    the word "to" occurring in sentences where something is demonstrated, shown, proved, or found

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "prove to" indicating assertions or claims

    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
    blooded
    -0.64
     registrations
    -0.63
    tta
    -0.62
     hamm
    -0.60
    querque
    -0.60
     lobb
    -0.58
    FTWARE
    -0.57
    ONSORED
    -0.57
     extradition
    -0.56
     Anthem
    -0.56
    POSITIVE LOGITS
    ggles
    1.03
    othy
    0.98
    psy
    0.90
     be
    0.84
    pless
    0.82
    asted
    0.82
    ilet
    0.79
    ying
    0.78
    wered
    0.76
     accelerate
    0.75
    Activations Density 0.068%

    No Known Activations