© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 3421
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a situation or outcome, especially around success or resolution

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the success or failure of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asus
    -0.80
    raltar
    -0.70
    inski
    -0.69
    gow
    -0.68
    aldi
    -0.67
     Frenzy
    -0.64
     Citation
    -0.64
    owicz
    -0.64
    shaw
    -0.62
    resy
    -0.61
    POSITIVE LOGITS
     differently
    1.15
     alright
    1.02
     nicely
    0.93
     okay
    0.93
     horribly
    0.86
     badly
    0.83
     beautifully
    0.82
     smoother
    0.81
     miser
    0.80
     favour
    0.79
    Activations Density 0.067%

    No Known Activations