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. 0-RES-JB
    6. 4298
    Prev
    Next
    INDEX
    Explanations

    references to specific numbered items or entities within a list

    oai_token-act-pair · gpt-3.5-turbo

    special character patterns or formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pioneer
    -0.80
     Cran
    -0.65
     courier
    -0.65
     Paradise
    -0.64
     Patrol
    -0.62
    iens
    -0.61
     seller
    -0.60
     Polar
    -0.59
     Anglo
    -0.59
     Evangel
    -0.58
    POSITIVE LOGITS
    ###
    4.48
    ####
    2.77
    ##
    2.64
     ###
    2.36
    ########
    2.24
    ################
    1.92
     ##
    1.72
    ################################
    1.60
     #####
    1.55
    #
    1.37
    Activations Density 0.033%

    No Known Activations