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. 10-RES-JB
    6. 2633
    Prev
    Next
    INDEX
    Explanations

    words related to accountability and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    references to financial pressures or burdens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocular
    -0.77
    canon
    -0.74
    ãĥĭ
    -0.71
    ãĤ¨ãĥ«
    -0.67
    series
    -0.67
    escription
    -0.65
    odiac
    -0.65
     alias
    -0.63
     playthrough
    -0.63
     clashed
    -0.62
    POSITIVE LOGITS
     taxpayers
    1.33
     millionaires
    1.24
     poverty
    1.22
     privatization
    1.22
     homelessness
    1.17
     subsidized
    1.17
     privat
    1.16
     trillions
    1.15
     impover
    1.14
     subsid
    1.13
    Activations Density 1.056%

    No Known Activations