© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 4719
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a quantification or evaluation of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a significant impact or consequence

    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
     craw
    -0.71
    tun
    -0.68
    rend
    -0.61
    IED
    -0.61
    iscovery
    -0.60
    cles
    -0.60
    aird
    -0.59
     thri
    -0.59
    hesion
    -0.58
    hered
    -0.58
    POSITIVE LOGITS
     satisfy
    0.73
     perfection
    0.72
    ilet
    0.70
    pport
    0.64
    anuts
    0.64
     compensate
    0.64
    ffee
    0.63
     infinity
    0.63
     ensure
    0.63
     suffice
    0.62
    Activations Density 0.135%

    No Known Activations