© 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. 10-RES-JB
    11. 2280
    Prev
    Next
    INDEX
    Explanations

    words related to something being clear, evident, or easily understandable

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "obvious" and related terms that suggest clear or evident concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntil
    -0.71
    bats
    -0.70
    agine
    -0.69
    nan
    -0.68
    rology
    -0.68
    ldom
    -0.68
    lished
    -0.68
    eries
    -0.67
    lain
    -0.66
    illas
    -0.66
    POSITIVE LOGITS
    iary
    1.18
     contradiction
    0.98
     culprit
    0.97
     obvious
    0.91
     implication
    0.90
     impossibility
    0.85
     absurdity
    0.84
     logical
    0.83
     drawback
    0.83
     progression
    0.82
    Activations Density 0.041%

    No Known Activations