© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 23153
    Prev
    Next
    INDEX
    Explanations

    exact instances of the word 'copy'

    oai_token-act-pair · gpt-3.5-turbo

    references to documents and versions of reports or legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Buddh
    -0.68
     Mecca
    -0.67
     Galile
    -0.64
    cest
    -0.62
     Pharaoh
    -0.61
     aber
    -0.61
    animate
    -0.59
     cult
    -0.58
     Dip
    -0.58
    agog
    -0.57
    POSITIVE LOGITS
     memorandum
    0.93
     revisions
    0.87
     briefing
    0.87
    ļéĨĴ
    0.86
     memo
    0.81
     outlining
    0.80
    andum
    0.79
     document
    0.78
     wording
    0.78
     submission
    0.76
    Activations Density 0.296%

    No Known Activations