© 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. 2-RES-JB
    11. 17351
    Prev
    Next
    INDEX
    Explanations

    specific names or references to someone or something named 'Dedmon'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dedicate" and its variations

    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
     Pastebin
    -0.68
     Ain
    -0.67
     Grail
    -0.66
    Trade
    -0.63
    FACE
    -0.62
    Arcade
    -0.60
     Surge
    -0.60
    picture
    -0.59
     Manip
    -0.59
    addons
    -0.58
    POSITIVE LOGITS
    ications
    1.22
    uced
    1.21
     ded
    1.19
    icates
    1.10
    icating
    1.06
    ication
    1.05
    ucing
    1.03
    icated
    0.99
    uces
    0.96
    uce
    0.95
    Activations Density 0.005%

    No Known Activations