© 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. 2-RES-JB
    11. 9386
    Prev
    Next
    INDEX
    Explanations

    mentions of political staff or workers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of staff or personnel in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Trend
    -0.68
    ãĥĸ
    -0.67
    olithic
    -0.66
     Bombay
    -0.65
     Frog
    -0.64
    asca
    -0.64
    Peace
    -0.64
    bolt
    -0.63
     Jub
    -0.61
    central
    -0.61
    POSITIVE LOGITS
     staffer
    1.03
     staffers
    1.01
    irtual
    0.98
    olor
    0.85
     reception
    0.83
     Emails
    0.76
     interns
    0.75
     salaries
    0.71
     memos
    0.68
     surn
    0.67
    Activations Density 0.014%

    No Known Activations