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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7-RES-JB
    6. 10551
    Prev
    Next
    INDEX
    Explanations

    special characters like 'Ċ' and 'Ŀ'

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     satell
    -0.83
     covenant
    -0.77
     periodic
    -0.76
     describ
    -0.75
     tast
    -0.74
     speeding
    -0.73
     neighb
    -0.73
     phased
    -0.71
     fermented
    -0.68
     treat
    -0.67
    POSITIVE LOGITS
    Advertisements
    1.28
    âĢ¢
    1.28
    ###
    1.23
    =-=-=-=-=-=-=-=-
    1.21
    âĹı
    1.20
    #
    1.20
    ·
    1.16
    ©
    1.15
    ________________________________________________________________
    1.15
    --------------------------------------------------------
    1.15
    Activations Density 0.367%

    No Known Activations