© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3283
    Prev
    Next
    INDEX
    Explanations

    phrases or statements confirming the truthfulness of a claim or fact

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "true" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uty
    -0.75
    adish
    -0.74
    ocene
    -0.72
    ILE
    -0.70
    ambo
    -0.69
    ourning
    -0.68
     Sections
    -0.68
    uled
    -0.67
     booths
    -0.67
    chains
    -0.67
    POSITIVE LOGITS
     true
    0.88
    true
    0.86
    quickShipAvailable
    0.80
    True
    0.77
     believers
    0.76
     TRUE
    0.76
    blooded
    0.72
     believer
    0.72
     è£ıè¦ļéĨĴ
    0.69
    ance
    0.68
    Activations Density 0.017%

    No Known Activations