© 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. 2-RES-JB
    11. 21651
    Prev
    Next
    INDEX
    Explanations

    technical terms or jargon

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "purpose" and related terms, as well as references to people and actions that significantly impact a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emb
    -0.74
    aeus
    -0.74
    inances
    -0.72
     embargo
    -0.72
    oms
    -0.70
     liv
    -0.66
     testament
    -0.65
    ĻĤ
    -0.65
    ogun
    -0.63
    izoph
    -0.63
    POSITIVE LOGITS
    purpose
    1.13
    theless
    0.95
    ãĥ¼ãĥĨãĤ£
    0.85
    ãĥĨãĤ£
    0.84
    POSE
    0.82
    tenance
    0.80
    ãĤ±
    0.79
    glers
    0.79
    ãĤ¢ãĥ«
    0.77
    ãĥ¯ãĥ³
    0.76
    Activations Density 0.022%

    No Known Activations