© 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. 2-RES-JB
    11. 9104
    Prev
    Next
    INDEX
    Explanations

    words related to desire or aspiration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental conditions and perceptions of desirability or envy

    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
    Reviewer
    -0.76
    ammy
    -0.71
    ppo
    -0.70
     Gum
    -0.67
    butt
    -0.64
    head
    -0.64
    die
    -0.63
    Books
    -0.63
    ramid
    -0.63
     Arcane
    -0.62
    POSITIVE LOGITS
     env
    1.21
    isions
    0.99
    env
    0.89
    ENTION
    0.85
    ours
    0.84
    igrated
    0.83
    oried
    0.81
    ancies
    0.80
    ounter
    0.80
    antly
    0.77
    Activations Density 0.006%

    No Known Activations