© 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. 23593
    Prev
    Next
    INDEX
    Explanations

    words related to a common name or surname "Pu" along with different variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "Pu" or "pu" in various contexts

    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
     Cosponsors
    -0.91
     GOODMAN
    -0.83
    hips
    -0.79
    Interstitial
    -0.76
    rawdownloadcloneembedreportprint
    -0.74
    tyard
    -0.73
    ãĤ·ãĥ£
    -0.73
     Corinth
    -0.71
    seeing
    -0.71
    Irish
    -0.70
    POSITIVE LOGITS
     Pu
    1.09
    pport
    0.93
     pu
    0.88
    Fu
    0.86
    cci
    0.84
    ente
    0.84
    etooth
    0.83
    asa
    0.82
    pees
    0.81
    eco
    0.80
    Activations Density 0.007%

    No Known Activations