© 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. 9128
    Prev
    Next
    INDEX
    Explanations

    phrases related to applying physical pressure or force

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "pressed" in various contexts

    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
    BIT
    -0.70
    ordinate
    -0.66
    beit
    -0.66
     Rays
    -0.64
    eway
    -0.63
    BuyableInstoreAndOnline
    -0.63
    ARP
    -0.62
     Pipeline
    -0.61
    ines
    -0.60
    ership
    -0.60
    POSITIVE LOGITS
     pressed
    1.21
    pressed
    1.03
    entary
    0.85
    ioned
    0.84
    press
    0.81
    olicy
    0.78
    ivated
    0.76
    nesday
    0.76
    ierrez
    0.76
    ļéĨĴ
    0.75
    Activations Density 0.012%

    No Known Activations