© 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. 2555
    Prev
    Next
    INDEX
    Explanations

    rankings or lists of items within different categories

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating rankings or lists of top items

    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
    norm
    -0.84
    icum
    -0.83
    redo
    -0.83
    roth
    -0.81
    protection
    -0.76
    arantine
    -0.75
    limited
    -0.75
    amar
    -0.74
    athered
    -0.74
    amination
    -0.73
    POSITIVE LOGITS
    Favorite
    1.02
     Worst
    0.86
     Influ
    0.85
     quotes
    0.79
     celeb
    0.76
     Bucket
    0.76
     unsolved
    0.76
     Celebrity
    0.76
     Places
    0.75
     Songs
    0.74
    Activations Density 0.305%

    No Known Activations