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

    Neuronpedia

    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. 6-RES-JB
    11. 10899
    Prev
    Next
    INDEX
    Explanations

    ingredients or cooking instructions, particularly those related to dried herbs and spices

    oai_token-act-pair · gpt-3.5-turbo

    references to drying and dehydrating processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ority
    -0.76
    adia
    -0.75
    ogun
    -0.75
    awaru
    -0.73
    ertodd
    -0.72
    ppard
    -0.72
    pload
    -0.71
    anco
    -0.69
    leading
    -0.68
    ucky
    -0.68
    POSITIVE LOGITS
     Goods
    0.78
     apr
    0.75
     fruits
    0.72
     fruit
    0.67
     herbs
    0.67
    ucing
    0.66
    caster
    0.65
    uce
    0.64
     drying
    0.64
    flower
    0.63
    Activations Density 0.020%

    No Known Activations