© 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 EvalsExportsinterp-engineNEWAPI 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. 16348
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are associated with a specific topic or concept

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating associations or relationships between concepts or conditions

    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
    stall
    -0.81
    hene
    -0.74
    ceans
    -0.72
    ASED
    -0.70
    mpeg
    -0.69
    aneers
    -0.69
    chal
    -0.68
    assi
    -0.68
    tein
    -0.66
    adra
    -0.66
    POSITIVE LOGITS
     newsp
    0.88
    ively
    0.88
     associations
    0.82
     associated
    0.80
    eering
    0.78
     behavi
    0.77
     activ
    0.76
    ativity
    0.74
     reperto
    0.74
    vertisements
    0.73
    Activations Density 0.014%

    No Known Activations