© 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. 2-RES-JB
    11. 17119
    Prev
    Next
    INDEX
    Explanations

    instances where an adjustment is made

    oai_token-act-pair · gpt-3.5-turbo

    terms related to adjustment and adaptability

    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
    gom
    -0.79
    jay
    -0.71
    OPA
    -0.71
    VP
    -0.71
    Champ
    -0.70
    ijk
    -0.69
    cart
    -0.68
     Furious
    -0.67
    Vs
    -0.66
     Chrys
    -0.66
    POSITIVE LOGITS
     adjustment
    1.16
     adjust
    1.15
     adjustments
    1.14
    adjust
    1.00
     adjusting
    0.99
     adjusts
    0.97
     Adjust
    0.89
    mble
    0.88
    ments
    0.88
     thresholds
    0.88
    Activations Density 0.012%

    No Known Activations