© 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. 10414
    Prev
    Next
    INDEX
    Explanations

    words with the prefix "par-" followed by a word starting with a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "par" or "parity."

    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
    ħĭ
    -0.92
    xia
    -0.82
    ¥µ
    -0.78
    éĹĺ
    -0.73
    doms
    -0.73
    hirt
    -0.73
    æĸ¹
    -0.73
    士
    -0.70
    ;;;;;;;;;;;;
    -0.69
    hower
    -0.67
    POSITIVE LOGITS
    rot
    0.86
     ILCS
    0.83
    allel
    0.81
    agraph
    0.80
    icularly
    0.80
    ret
    0.80
    vati
    0.78
    onto
    0.77
    icy
    0.77
    par
    0.76
    Activations Density 0.010%

    No Known Activations