© 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. 8-RES-JB
    11. 3266
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a condition or alternative course of action

    oai_token-act-pair · gpt-3.5-turbo

    affirmations or declarations about existence and state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nown
    -0.79
     largeDownload
    -0.74
    vant
    -0.72
    eatured
    -0.72
    ventures
    -0.68
    ateg
    -0.67
    thren
    -0.67
    vantage
    -0.66
    fell
    -0.66
    itures
    -0.65
    POSITIVE LOGITS
    olation
    0.75
    anke
    0.71
     Solitaire
    0.66
     annoyance
    0.65
     occasional
    0.65
     silence
    0.64
     Goat
    0.61
    GGGG
    0.60
    inka
    0.60
     pure
    0.60
    Activations Density 0.076%

    No Known Activations