© 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. 7755
    Prev
    Next
    INDEX
    Explanations

    the name "Pereira" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Pere" and its variations in the document

    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
    INESS
    -0.74
     shame
    -0.68
     Columb
    -0.64
    AMES
    -0.64
    imates
    -0.63
    _>
    -0.61
    OWN
    -0.60
    ãĤ¢ãĥ«
    -0.60
     checkout
    -0.60
     Nightmares
    -0.59
    POSITIVE LOGITS
     Pere
    1.21
    tti
    1.11
     Pengu
    0.88
    tsky
    0.86
    agin
    0.85
    ments
    0.84
    fw
    0.84
    achy
    0.83
    gon
    0.82
    folios
    0.80
    Activations Density 0.009%

    No Known Activations