© 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. 2-RES-JB
    11. 11600
    Prev
    Next
    INDEX
    Explanations

    references to the media platform "Crunchyroll"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the media outlet Crunchyroll

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ounter
    -0.75
    س
    -0.75
    NRS
    -0.72
    ATHER
    -0.71
     Lama
    -0.71
    JB
    -0.70
    ather
    -0.68
    cedes
    -0.66
    DCS
    -0.65
    ÙĦ
    -0.65
    POSITIVE LOGITS
     Crunch
    1.15
    Crunch
    1.00
    imation
    0.85
     Rating
    0.77
    aneers
    0.77
    pedia
    0.74
    anos
    0.73
    Å«
    0.73
    zeb
    0.72
    icer
    0.70
    Activations Density 0.012%

    No Known Activations