© 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. 6349
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    oai_token-act-pair · gpt-3.5-turbo

    copyright and publishing information

    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
    nikov
    -0.71
    soDeliveryDate
    -0.64
    brainer
    -0.63
    hello
    -0.63
     footsteps
    -0.61
    idges
    -0.61
     haunt
    -0.60
    enable
    -0.59
    igraph
    -0.58
    igrate
    -0.58
    POSITIVE LOGITS
    Ħ¢
    0.75
    çīĪ
    0.73
    alysed
    0.72
     Flavoring
    0.70
     Ltd
    0.69
    ©¶æ¥µ
    0.69
    \/\/
    0.68
     LLC
    0.66
     [];
    0.65
    ãĥĥãĥĪ
    0.64
    Activations Density 0.066%

    No Known Activations