© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1010
    Prev
    Next
    INDEX
    Explanations

    references to news headlines or current events

    oai_token-act-pair · gpt-3.5-turbo

    references to various media content and significant events or figures

    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
    Abstract
    -0.83
     ().
    -0.83
    —"
    -0.78
    âĢķ
    -0.73
     CrossRef
    -0.71
    ¶
    -0.68
     administr
    -0.67
    Contents
    -0.65
    isSpecialOrderable
    -0.63
    ":["
    -0.63
    POSITIVE LOGITS
    edes
    0.81
    attled
    0.81
     Emails
    0.77
    htaking
    0.77
    roversial
    0.73
     slams
    0.70
    atican
    0.68
    anyahu
    0.67
    rieving
    0.67
    ]'
    0.66
    Activations Density 0.245%

    No Known Activations