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. 17268
    Prev
    Next
    INDEX
    Explanations

    phrases referring to an unspecified, broad, and non-specific group within a context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "some" indicating indefinite quantities or examples

    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
    Balt
    -0.78
    ileaks
    -0.75
    Putin
    -0.72
    multipl
    -0.69
    assis
    -0.68
    TPPStreamerBot
    -0.67
    iggurat
    -0.67
    BuyableInstoreAndOnline
    -0.67
    edin
    -0.64
    itud
    -0.64
    POSITIVE LOGITS
     countries
    1.18
     situations
    1.15
     companies
    1.11
     people
    1.10
     individuals
    1.10
     manufacturers
    1.09
     jurisdictions
    1.09
     cultures
    1.06
     brands
    1.04
     cases
    1.04
    Activations Density 0.185%

    No Known Activations