© 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. 8-RES-JB
    11. 22401
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical attributes and characteristics, such as textures, tastes or sensations

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to physical and tangible concepts, particularly those associated with temperature and intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.78
    ²¾
    -0.73
    UA
    -0.70
    ãĥĥ
    -0.69
    =-=-=-=-
    -0.69
    ãĥĥãĥī
    -0.69
    SEA
    -0.66
    ģĸ
    -0.65
    anton
    -0.62
    Fab
    -0.62
    POSITIVE LOGITS
    nered
    1.02
    nings
    0.92
    ounters
    0.87
     (>
    0.70
    hens
    0.69
     syndrome
    0.68
    dding
    0.64
    antry
    0.64
     (<
    0.64
    iasis
    0.64
    Activations Density 0.511%

    No Known Activations