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. 1-RES-JB
    6. 13828
    Prev
    Next
    INDEX
    Explanations

    statements or comments

    oai_token-act-pair · gpt-3.5-turbo

    expressions of self-reflection and inner dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.53
    istani
    -0.43
    ForgeModLoader
    -0.43
     antioxid
    -0.41
    istan
    -0.41
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.39
    channelAvailability
    -0.38
     srfAttach
    -0.37
    Zone
    -0.37
    thumbnails
    -0.37
    POSITIVE LOGITS
    bye
    0.49
    GGGG
    0.46
    riel
    0.45
    ITNESS
    0.45
    ĻĤ
    0.45
    rb
    0.44
    oooooooo
    0.44
    uca
    0.44
    apego
    0.44
    ierre
    0.43
    Activations Density 5.962%

    No Known Activations