© 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. 10768
    Prev
    Next
    INDEX
    Explanations

    formal language related to accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    references to achievements and accomplishments

    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
    odynamic
    -0.69
    othing
    -0.68
    oxin
    -0.67
    pper
    -0.66
    esthetic
    -0.66
    trop
    -0.66
    ondo
    -0.66
    ned
    -0.66
    sey
    -0.63
    creen
    -0.62
    POSITIVE LOGITS
     accomplishment
    1.17
     achievement
    1.15
     achievements
    1.11
     achie
    1.03
     attainment
    1.03
     feats
    1.02
     Achievement
    1.01
    rious
    0.98
     accomplishments
    0.98
     accomplished
    0.98
    Activations Density 0.046%

    No Known Activations