© 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. 4-RES-JB
    6. 17124
    Prev
    Next
    INDEX
    Explanations

    words related to negation or uselessness

    oai_token-act-pair · gpt-3.5-turbo

    words containing the suffix "aught" or "ought."

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

    No Comments

    Negative Logits
    cit
    -0.72
    seys
    -0.70
    Journal
    -0.68
    ographers
    -0.66
    clerosis
    -0.64
     Lieberman
    -0.63
    Bomb
    -0.61
     Jericho
    -0.59
    culated
    -0.57
    cul
    -0.56
    POSITIVE LOGITS
    nir
    0.83
    ãĤ¤ãĥĪ
    0.81
    ishly
    0.81
    ãĤ¦ãĤ¹
    0.80
    ily
    0.80
    inen
    0.79
    tackle
    0.79
    entimes
    0.78
    iless
    0.77
    iful
    0.76
    Activations Density 0.011%

    No Known Activations