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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 3463
    Prev
    Next
    INDEX
    Explanations

    phrases related to making a situation easier or clearer through legislation or announcements

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the ease or clarity of actions or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     owes
    -0.75
    orsi
    -0.73
    inguished
    -0.64
    edIn
    -0.61
    atur
    -0.57
    Avg
    -0.57
     reper
    -0.57
    ethy
    -0.56
    ibles
    -0.56
    76561
    -0.56
    POSITIVE LOGITS
     abundantly
    1.24
     easier
    1.23
     harder
    1.22
     impossible
    1.15
     clear
    1.15
     difficult
    1.08
     clearer
    1.02
     easy
    1.00
     tougher
    0.98
     crystal
    0.97
    Activations Density 0.057%

    No Known Activations