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. 9-RES-JB
    6. 10850
    Prev
    Next
    INDEX
    Explanations

    terms related to programming languages and technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to programming experience and unfamiliarity with programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teasp
    -0.93
    earchers
    -0.92
    terness
    -0.89
    Residents
    -0.81
    egu
    -0.77
    nown
    -0.75
     exting
    -0.75
    letcher
    -0.74
    erity
    -0.73
     attendant
    -0.73
    POSITIVE LOGITS
     RPGs
    0.90
     this
    0.83
     FF
    0.81
     Minecraft
    0.80
     Bleach
    0.79
     Magic
    0.78
     GG
    0.78
     CoC
    0.78
     anything
    0.77
     Django
    0.77
    Activations Density 0.608%

    No Known Activations