© 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. 2-RES-JB
    11. 21593
    Prev
    Next
    INDEX
    Explanations

    verbs related to strong physical actions or confrontations

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "range" and related concepts

    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
    ç«
    -0.79
    veland
    -0.74
    çĶŁ
    -0.73
    ridor
    -0.70
    xia
    -0.70
    odor
    -0.70
    zza
    -0.68
    inth
    -0.67
    æĺ
    -0.67
    percent
    -0.67
    POSITIVE LOGITS
    anged
    0.97
    enger
    0.74
    erent
    0.72
    engers
    0.70
    hell
    0.70
    cffffcc
    0.68
     minded
    0.67
     Warfare
    0.66
     bang
    0.66
    eals
    0.65
    Activations Density 0.017%

    No Known Activations