© 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. 2-RES-JB
    11. 4543
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hat"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hat" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.79
    interstitial
    -0.68
     medic
    -0.68
     glutamate
    -0.62
     tuning
    -0.60
     Augusta
    -0.60
     Superior
    -0.59
    aceous
    -0.59
    Reviewer
    -0.59
     billing
    -0.59
    POSITIVE LOGITS
    soever
    1.01
    chery
    1.00
    chet
    0.99
    dar
    0.88
    rina
    0.86
    tha
    0.81
    ia
    0.81
    ney
    0.80
    cher
    0.79
    rance
    0.78
    Activations Density 0.003%

    No Known Activations