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

    Neuronpedia

    APICircuit 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. 1838
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by a number, indicating a location or quantity

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and their associations with time or location

    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
    respective
    -0.65
     contradictory
    -0.63
     accumulated
    -0.63
     importantly
    -0.63
    odd
    -0.59
     seldom
    -0.59
    ——
    -0.59
     rarely
    -0.58
     selves
    -0.58
    information
    -0.57
    POSITIVE LOGITS
     Depth
    0.76
     Lifetime
    0.74
     Desert
    0.72
     Telescope
    0.71
     Birthday
    0.70
     AZ
    0.70
     Himself
    0.70
     whom
    0.69
     Screw
    0.69
     steroids
    0.69
    Activations Density 0.422%

    No Known Activations