© 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. 1238
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical characteristics or actions associated with a particular person

    oai_token-act-pair · gpt-3.5-turbo

    descriptions or references to specific individuals, particularly in a narrative context

    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
    Shape
    -0.61
    Picture
    -0.61
    ':
    -0.55
     Belfast
    -0.54
    Firstly
    -0.53
     Patreon
    -0.52
     cryptocurrency
    -0.51
    lations
    -0.51
    \":
    -0.51
    Brexit
    -0.51
    POSITIVE LOGITS
    .")
    0.79
    )."
    0.78
    ]."
    0.67
    .'"
    0.65
     Vaugh
    0.62
    .).
    0.61
     }}
    0.61
    "/>
    0.61
    ").
    0.61
    '."
    0.60
    Activations Density 2.973%

    No Known Activations