© 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. 4-RES-JB
    11. 7405
    Prev
    Next
    INDEX
    Explanations

    contradictions or unexpected combinations within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "yet" in various contexts, indicating contrast or exception

    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
    rities
    -0.86
    tein
    -0.71
    regate
    -0.68
    edu
    -0.67
    ancial
    -0.66
    scribe
    -0.66
    rats
    -0.66
    gnu
    -0.64
    puters
    -0.63
    ilitating
    -0.63
    POSITIVE LOGITS
     somehow
    0.79
     again
    0.68
     manages
    0.67
     inexpl
    0.67
     strangely
    0.67
     mirac
    0.66
    heric
    0.66
     managed
    0.63
    forth
    0.63
     surpass
    0.63
    Activations Density 0.023%

    No Known Activations