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. 7-RES-JB
    6. 5417
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express criticism or negative opinions about individuals or entities, particularly political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    api
    -0.80
    cue
    -0.71
    OURCE
    -0.71
    igmatic
    -0.69
    aceae
    -0.69
    ulo
    -0.69
    rh
    -0.68
    alde
    -0.67
    ZA
    -0.66
    ĸļ
    -0.65
    POSITIVE LOGITS
     fellow
    0.82
     homosexuality
    0.79
     perceived
    0.72
     politicians
    0.71
     gays
    0.71
     capitalism
    0.71
    jad
    0.70
     homosexuals
    0.69
     communism
    0.69
     him
    0.69
    Activations Density 0.217%

    No Known Activations