© 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. 1362
    Prev
    Next
    INDEX
    Explanations

    references to or occurrences of the word "essay" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of essays or related content about essays

    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
    rals
    -0.71
    generic
    -0.65
     Lumpur
    -0.65
    ategory
    -0.64
    Lago
    -0.64
    gone
    -0.63
     Geo
    -0.63
    cling
    -0.63
    eco
    -0.61
    CI
    -0.59
    POSITIVE LOGITS
     essay
    1.03
     essays
    0.91
    ertation
    0.79
    worm
    0.76
    worms
    0.74
    istical
    0.74
    ists
    0.73
    abal
    0.71
    Writing
    0.70
     Slam
    0.70
    Activations Density 0.007%

    No Known Activations