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. 3-RES-JB
    6. 6838
    Prev
    Next
    INDEX
    Explanations

    past tense verbs that describe physical actions performed on a person

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     backdrop
    -0.49
     CLR
    -0.45
     purportedly
    -0.43
     ///
    -0.43
     markedly
    -0.41
     Vulkan
    -0.41
     AMERICA
    -0.41
     blight
    -0.40
     substantially
    -0.39
     reportedly
    -0.39
    POSITIVE LOGITS
    poke
    0.62
     myself
    0.55
    laughs
    0.50
     butterflies
    0.49
     friends
    0.46
    fortable
    0.45
     happiest
    0.44
     fuckin
    0.44
    â̦"
    0.44
     gonna
    0.44
    Activations Density 3.136%

    No Known Activations