© 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. 3016
    Prev
    Next
    INDEX
    Explanations

    instances of the word "success" being in close proximity to other words

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of success

    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
    inki
    -0.75
    esthesia
    -0.73
     beds
    -0.72
     needles
    -0.70
    isted
    -0.68
    Border
    -0.67
    jit
    -0.63
    ros
    -0.62
    venants
    -0.61
    pron
    -0.61
    POSITIVE LOGITS
    successfully
    0.92
    tein
    0.76
     successfully
    0.73
    akedown
    0.71
     teamwork
    0.70
    successful
    0.69
    ãĥ¡
    0.68
     feats
    0.68
     Yel
    0.64
     bidder
    0.64
    Activations Density 0.248%

    No Known Activations