Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 6-RES-JB
    6. 17079
    Prev
    Next
    INDEX
    Explanations

    phrases related to secret agents or espionage activities

    oai_token-act-pair · gpt-3.5-turbo

    references to agents or authoritative figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -1.09
    lihood
    -1.03
    etooth
    -0.83
    FACE
    -0.82
    orld
    -0.74
    ĸļ
    -0.69
    phrine
    -0.67
    cept
    -0.66
    nz
    -0.65
    imeo
    -0.64
    POSITIVE LOGITS
     prov
    0.94
     agent
    0.94
    sov
    0.86
     agents
    0.85
     Agent
    0.85
    agent
    0.85
    agents
    0.83
    arial
    0.78
    osa
    0.78
     Agents
    0.78
    Activations Density 0.030%

    No Known Activations