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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3663
    Prev
    Next
    INDEX
    Explanations

    comparisons between different individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases emphasizing similarities and differences

    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
    iHUD
    -0.73
    UCT
    -0.67
    WIND
    -0.66
    endiary
    -0.66
     EVENTS
    -0.61
     Accessed
    -0.60
    isin
    -0.58
    Constructed
    -0.57
     longitudinal
    -0.56
     respectively
    -0.55
    POSITIVE LOGITS
     anybody
    1.24
     anyone
    1.16
     usual
    1.05
     others
    1.02
     everybody
    0.99
     everyone
    0.97
    average
    0.90
     myself
    0.86
    everyone
    0.80
     most
    0.78
    Activations Density 0.131%

    No Known Activations