© 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. 8-RES-JB
    11. 20049
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing evidence or proof

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate proof or evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.84
     meanwhile
    -0.68
    ornings
    -0.66
    ÃĥÃĤ
    -0.65
    entimes
    -0.65
    vice
    -0.62
    ļéĨĴ
    -0.61
    health
    -0.61
    Fresh
    -0.60
    itored
    -0.59
    POSITIVE LOGITS
     phenomena
    0.78
    geries
    0.77
     fallacy
    0.74
     Hegel
    0.73
     theorem
    0.71
     cipher
    0.67
     hypothesis
    0.66
     plagiar
    0.66
     Canaver
    0.66
     causation
    0.64
    Activations Density 0.961%

    No Known Activations