© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 21801
    Prev
    Next
    INDEX
    Explanations

    the word "Agent" or related variations

    oai_token-act-pair · gpt-3.5-turbo

    references to agents, especially in a context related to intelligence or espionage

    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
    lihood
    -1.07
    issance
    -0.94
    FACE
    -0.75
    etooth
    -0.75
    ths
    -0.74
    ĸļ
    -0.71
    orld
    -0.70
    phrine
    -0.69
    cept
    -0.66
    nz
    -0.65
    POSITIVE LOGITS
     prov
    0.99
     agent
    0.90
     Agent
    0.88
    agent
    0.87
    sov
    0.84
    agents
    0.79
     agents
    0.78
    inates
    0.78
    iola
    0.75
    anova
    0.75
    Activations Density 0.034%

    No Known Activations