Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 4051
    Prev
    Next
    INDEX
    Explanations

    the surname "Patterson."

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly "Patterson" and "Wein."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.87
    д
    -0.76
    SEE
    -0.75
    ERAL
    -0.75
    ORGE
    -0.72
    pipe
    -0.65
    DIR
    -0.64
    ¥
    -0.63
    AMES
    -0.62
    hire
    -0.62
    POSITIVE LOGITS
     Patterson
    1.23
    terson
    0.85
    riott
    0.78
     eleph
    0.76
    ricia
    0.72
    icons
    0.70
     Leban
    0.70
     newcom
    0.69
    arella
    0.68
    olini
    0.67
    Activations Density 0.008%

    No Known Activations