© 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. 1-RES-JB
    11. 22588
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to destruction or collapse

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the film industry and movie production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atron
    -0.92
    lon
    -0.82
    ia
    -0.82
    lock
    -0.81
    ide
    -0.81
    kish
    -0.80
    ibel
    -0.80
    ious
    -0.79
    ãĤ£
    -0.78
    wald
    -0.78
    POSITIVE LOGITS
    INGS
    1.35
    ER
    1.35
    BOOK
    1.32
    ERS
    1.32
    ING
    1.31
    WAYS
    1.30
    ANCE
    1.30
    FORM
    1.30
    FORE
    1.27
    BALL
    1.27
    Activations Density 0.066%

    No Known Activations