© 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. 4-RES-JB
    11. 2779
    Prev
    Next
    INDEX
    Explanations

    words related to cutting or separating something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "seam" and its related forms

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

    No Comments

    Negative Logits
    initely
    -0.80
    INGTON
    -0.74
     hoops
    -0.73
    etheless
    -0.71
    ashtra
    -0.70
    SHIP
    -0.69
    £ı
    -0.69
    enhagen
    -0.68
    hetti
    -0.65
    ohydrate
    -0.64
    POSITIVE LOGITS
    eps
    1.04
    perate
    1.03
    eker
    0.96
    pt
    0.96
    vel
    0.95
    ve
    0.94
    leanor
    0.93
    eding
    0.92
    vent
    0.91
    clusion
    0.90
    Activations Density 0.012%

    No Known Activations