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. 11-RES-JB
    6. 4340
    Prev
    Next
    INDEX
    Explanations

    color combinations, particularly black and white

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Architects
    -0.82
    Bus
    -0.70
    BIL
    -0.69
    */(
    -0.68
    Cry
    -0.68
    MJ
    -0.66
    utsu
    -0.65
    VERTISEMENT
    -0.64
    ctors
    -0.64
     Mutual
    -0.64
    POSITIVE LOGITS
     white
    1.18
    white
    1.13
     Decker
    1.07
     Hispanic
    1.06
     Latino
    1.02
     whites
    1.01
     brown
    1.01
     grey
    0.90
     yellow
    0.90
     Latinos
    0.86
    Activations Density 0.060%

    No Known Activations