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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 10-RES-JB
    6. 15910
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes or actions being anticipated or planned in an organized setting

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts, indicating connections or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sunder
    -0.71
    ouses
    -0.70
    é¾įå¥ij士
    -0.70
    edIn
    -0.69
    uses
    -0.68
     Chosen
    -0.67
    owitz
    -0.67
     Ott
    -0.67
    akis
    -0.66
     Winners
    -0.66
    POSITIVE LOGITS
     intelligence
    0.99
     telecommunications
    0.99
     wellness
    0.99
     logistical
    0.97
     environmental
    0.96
     telecom
    0.94
     entertainment
    0.92
     communications
    0.92
     behavioral
    0.92
     beverage
    0.91
    Activations Density 0.159%

    No Known Activations