© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 5506
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases related to search engine optimization (SEO)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to keywords

    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
    erest
    -0.77
    ardy
    -0.72
     Ryder
    -0.72
     Tob
    -0.70
    arus
    -0.69
     Democr
    -0.69
    asio
    -0.68
    oyer
    -0.68
    kens
    -0.68
    ares
    -0.67
    POSITIVE LOGITS
     keywords
    1.03
     keyword
    0.97
    ãĥ£
    0.89
    antha
    0.87
    word
    0.82
     phrase
    0.80
     sear
    0.80
    eering
    0.77
     stuffing
    0.76
     searches
    0.76
    Activations Density 0.010%

    No Known Activations