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. 9192
    Prev
    Next
    INDEX
    Explanations

    words related to offering or receiving support

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the concept of support and mutual aid

    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
     teasp
    -0.78
    iren
    -0.74
    ptoms
    -0.73
    æ©Ł
    -0.72
    cloneembedreportprint
    -0.70
     proble
    -0.68
    vern
    -0.68
    escription
    -0.68
    DeliveryDate
    -0.67
    orp
    -0.67
    POSITIVE LOGITS
     charities
    0.82
     independence
    0.79
     efforts
    0.76
     initiatives
    0.76
     Proposition
    0.76
     ongoing
    0.73
     them
    0.73
     exemplary
    0.72
     principled
    0.71
    ively
    0.71
    Activations Density 0.061%

    No Known Activations