© 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. 8662
    Prev
    Next
    INDEX
    Explanations

    names or mentions of the individual 'Merv'

    oai_token-act-pair · gpt-3.5-turbo

    the word "erv" and its variations, indicating a focus on a specific subject or entity related to the context in the document

    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
    fine
    -0.64
    ¿½
    -0.64
    ¦
    -0.60
    Ħ¢
    -0.59
    riad
    -0.58
    holders
    -0.58
    comb
    -0.57
    ------------------------------------------------
    -0.57
    DIV
    -0.57
     saf
    -0.56
    POSITIVE LOGITS
    asive
    1.16
    atism
    1.07
    iew
    1.00
    oice
    0.98
    okes
    0.96
    ideo
    0.94
    icious
    0.91
    oir
    0.91
    igion
    0.90
    idential
    0.90
    Activations Density 0.024%

    No Known Activations