© 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. 22314
    Prev
    Next
    INDEX
    Explanations

    phrases related to email newsletters

    oai_token-act-pair · gpt-3.5-turbo

    references to newsletters

    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
    abase
    -0.64
     reformed
    -0.60
     Gaw
    -0.59
     Ow
    -0.58
     Catalyst
    -0.57
     barg
    -0.55
     fortun
    -0.53
     Galile
    -0.53
     ord
    -0.52
     Camel
    -0.52
    POSITIVE LOGITS
    usalem
    0.74
    veyard
    0.73
     actionGroup
    0.71
    isode
    0.70
     IMAGES
    0.69
    sylv
    0.68
    é¾įå¥ij士
    0.66
    umbnails
    0.66
    ļéĨĴ
    0.64
    ĸļ
    0.63
    Activations Density 0.015%

    No Known Activations