© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 12335
    Prev
    Next
    INDEX
    Explanations

    references to novels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "novel"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    older
    -0.63
     McMahon
    -0.63
    ++++
    -0.62
    adow
    -0.62
    angelo
    -0.59
    cler
    -0.59
    yg
    -0.59
    SOURCE
    -0.58
    tics
    -0.58
    EV
    -0.57
    POSITIVE LOGITS
    ties
    1.04
    izations
    1.00
    isations
    0.99
    culosis
    0.91
    isation
    0.90
     adaptation
    0.89
     novel
    0.89
     novels
    0.86
    acters
    0.82
    izer
    0.80
    Activations Density 0.014%

    No Known Activations