© 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. 7-RES-JB
    11. 20630
    Prev
    Next
    INDEX
    Explanations

    phrases related to something being new, recent, or just starting

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "fresh" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rael
    -0.75
    Ĥİ
    -0.65
    adian
    -0.62
    oried
    -0.62
    aylor
    -0.61
     Donation
    -0.60
    orem
    -0.59
    owered
    -0.59
     incorrectly
    -0.59
     Loren
    -0.59
    POSITIVE LOGITS
    ness
    1.20
    lish
    1.04
    lings
    0.81
    water
    0.81
    foundland
    0.80
     scratch
    0.77
     fresh
    0.76
    lins
    0.75
    cit
    0.75
    lic
    0.75
    Activations Density 0.033%

    No Known Activations