© 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. 3-RES-JB
    11. 12968
    Prev
    Next
    INDEX
    Explanations

    adjectives or nouns related to groups or partnerships

    oai_token-act-pair · gpt-3.5-turbo

    references to collective groups or actions

    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
    ocrates
    -0.78
    jack
    -0.76
    xual
    -0.74
    geon
    -0.73
    nz
    -0.72
    gun
    -0.69
    ĪĴ
    -0.69
    lyn
    -0.67
    nen
    -0.67
    boats
    -0.67
    POSITIVE LOGITS
     bargaining
    1.15
     collective
    1.02
     collectively
    0.78
     endeavour
    0.78
     gasp
    0.78
     effort
    0.76
     uprising
    0.75
     anthem
    0.74
    ãĤ¢ãĥ«
    0.71
     agreement
    0.70
    Activations Density 0.010%

    No Known Activations