© 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. 10-RES-JB
    11. 10306
    Prev
    Next
    INDEX
    Explanations

    words related to media or the media industry

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with mediocrity and mediating circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flake
    -0.74
    eele
    -0.71
     Slate
    -0.70
    schild
    -0.61
    theless
    -0.61
     Dangerous
    -0.61
    laus
    -0.61
     Mare
    -0.60
    lain
    -0.60
     Sacrifice
    -0.60
    POSITIVE LOGITS
    ocr
    1.35
    ptions
    1.06
    arial
    0.99
    aries
    0.97
    inally
    0.96
    ators
    0.96
    inarily
    0.95
    arious
    0.94
    ocre
    0.92
    acent
    0.92
    Activations Density 0.078%

    No Known Activations