© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 23572
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or organizational matters that are important or high priority

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "agenda" and its variations

    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
    igi
    -0.76
    BuyableInstoreAndOnline
    -0.71
    amping
    -0.69
    pmwiki
    -0.69
    apy
    -0.69
    thens
    -0.69
    thood
    -0.68
    untary
    -0.68
    imb
    -0.67
    iability
    -0.67
    POSITIVE LOGITS
     agenda
    1.46
     agendas
    1.26
    eering
    0.97
     Agenda
    0.95
    eers
    0.86
    matic
    0.82
    olicy
    0.82
    llor
    0.74
     ploy
    0.74
     lun
    0.73
    Activations Density 0.013%

    No Known Activations