© 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. 4-RES-JB
    11. 22119
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to extreme or significant change

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "radical" and its variations, indicating a focus on significant or transformative changes

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

    No Comments

    Negative Logits
    sburgh
    -0.79
    ORD
    -0.78
    ords
    -0.71
    ammad
    -0.70
    fman
    -0.69
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
    çİĭ
    -0.67
    ursed
    -0.66
    anooga
    -0.65
    Mich
    -0.65
    POSITIVE LOGITS
     departure
    0.91
     chic
    0.89
     redef
    0.81
     fringe
    0.81
    itarian
    0.80
     rethink
    0.76
    imental
    0.73
     feminist
    0.73
     revolution
    0.73
    ising
    0.71
    Activations Density 0.020%

    No Known Activations