© 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. 357
    Prev
    Next
    INDEX
    Explanations

    the word "offset" or variations of it

    oai_token-act-pair · gpt-4-turbo

    word or phrases related to offsetting or counterbalancing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial adjustments or compensatory measures

    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
    Export
    -0.75
    =-=-=-=-=-=-=-=-
    -0.71
    akin
    -0.67
    otine
    -0.65
    wordpress
    -0.64
    zech
    -0.63
    ogy
    -0.63
    atom
    -0.63
     Fuk
    -0.61
    ostic
    -0.60
    POSITIVE LOGITS
    ting
    1.05
     offset
    0.97
    mented
    0.93
     offsets
    0.88
    ments
    0.88
    balance
    0.76
    offset
    0.74
    ment
    0.73
    irection
    0.73
     overflow
    0.72
    Activations Density 0.008%

    No Known Activations