© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9187
    Prev
    Next
    INDEX
    Explanations

    words related to prestigious awards and honors

    oai_token-act-pair · gpt-3.5-turbo

    references to Nobel and Pulitzer Prize winners and their associated achievements

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

    No Comments

    Negative Logits
    versions
    -0.77
    selves
    -0.74
     CY
    -0.72
    ãĥ¯ãĥ³
    -0.71
    town
    -0.69
    ded
    -0.68
    ALTH
    -0.66
    ãĤ®
    -0.65
    dest
    -0.64
    66666666
    -0.62
    POSITIVE LOGITS
     Prize
    1.23
     laureate
    1.05
     awarded
    0.96
     medal
    0.93
     laure
    0.92
     nominations
    0.88
     prizes
    0.86
     Medal
    0.86
     Winners
    0.85
     medals
    0.84
    Activations Density 0.016%

    No Known Activations