© 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. 4-RES-JB
    11. 9135
    Prev
    Next
    INDEX
    Explanations

    scientific hypotheses or theories

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific hypotheses and their testing

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

    No Comments

    Negative Logits
    artney
    -0.90
    dos
    -0.80
    thumbnails
    -0.78
    luster
    -0.76
    ookie
    -0.76
    cler
    -0.75
    pine
    -0.73
    Interstitial
    -0.72
    sung
    -0.72
    nia
    -0.72
    POSITIVE LOGITS
     hypothesis
    1.00
    icist
    0.99
     conjecture
    0.92
     hypothes
    0.89
     hypotheses
    0.81
     inferred
    0.78
     assumption
    0.78
     theory
    0.77
     premise
    0.77
     extrap
    0.76
    Activations Density 0.024%

    No Known Activations