© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 6860
    Prev
    Next
    INDEX
    Explanations

    words related to maturation and physical surfaces like mats or materials

    oai_token-act-pair · gpt-3.5-turbo

    references to mats and their occurrences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.89
    ngth
    -0.88
    vous
    -0.77
    FUL
    -0.75
    FINE
    -0.69
    hower
    -0.66
    IGHTS
    -0.65
    Ô
    -0.64
    æĸ¹
    -0.62
    GROUP
    -0.62
    POSITIVE LOGITS
    rices
    1.34
    hematically
    1.30
    urity
    1.07
    rice
    0.96
    imes
    0.93
    rics
    0.91
    hemat
    0.90
    het
    0.90
    ting
    0.89
    aroo
    0.89
    Activations Density 0.005%

    No Known Activations