© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4356
    Prev
    Next
    INDEX
    Explanations

    specific mentions of tax returns, usually with an emphasis on the action of filing or claiming

    oai_token-act-pair · gpt-3.5-turbo

    references to tax returns

    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
    TAG
    -0.69
    hemat
    -0.67
    Administ
    -0.67
    kson
    -0.66
    éĹĺ
    -0.65
    acht
    -0.63
    vern
    -0.62
    pport
    -0.62
    Cola
    -0.61
    alys
    -0.60
    POSITIVE LOGITS
    pring
    0.89
     Returns
    0.84
    earchers
    0.82
     returns
    0.79
    Returns
    0.77
    lash
    0.77
     Returning
    0.77
    cand
    0.72
    eed
    0.72
    nil
    0.71
    Activations Density 0.010%

    No Known Activations