© 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. 0-RES-JB
    11. 15482
    Prev
    Next
    INDEX
    Explanations

    verbs related to examination or assessment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reviewing."

    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
    SPONSORED
    -0.66
    Percent
    -0.62
     bet
    -0.60
    FU
    -0.59
    Args
    -0.58
    BN
    -0.56
    ield
    -0.56
    olitics
    -0.56
    HY
    -0.56
     origin
    -0.55
    POSITIVE LOGITS
     reviewing
    3.06
     analyzing
    2.23
     examining
    2.18
     evaluating
    2.13
     assessing
    2.12
     analys
    2.10
     interviewing
    2.00
     researching
    1.92
     discussing
    1.83
     studying
    1.82
    Activations Density 0.023%

    No Known Activations