© 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. 6-RES-JB
    11. 11747
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking or finding individuals for various purposes such as residents, employees, volunteers, allies, enemies, partners, customers, drummer, clients, people, and sponsors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to relationships, partnerships, and associations

    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
    indu
    -0.61
     Belt
    -0.59
     Manufact
    -0.58
    ļéĨĴ
    -0.55
     Products
    -0.55
     Amendments
    -0.54
     poorest
    -0.54
    vertis
    -0.54
     Correspond
    -0.53
     commencement
    -0.53
    POSITIVE LOGITS
    hip
    1.29
    hips
    1.13
     willing
    0.81
     capable
    0.77
    thood
    0.77
     whom
    0.77
     roaming
    0.76
     who
    0.74
     altogether
    0.72
     footing
    0.72
    Activations Density 0.396%

    No Known Activations