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. 0-RES-JB
    6. 5366
    Prev
    Next
    INDEX
    Explanations

    words related to terms in various fields such as mathematics, medicine, and diplomacy that end with the suffix '-atic'

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific categories or types of artistic expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jail
    -0.65
     vow
    -0.63
     laborers
    -0.62
    UID
    -0.62
     subcontract
    -0.62
     order
    -0.60
     dwarves
    -0.60
     shovel
    -0.59
     Haz
    -0.59
     Mans
    -0.59
    POSITIVE LOGITS
    atic
    4.67
    atically
    3.22
    atics
    3.06
    atical
    2.23
    actic
    1.56
    matic
    1.50
    asis
    1.45
    atis
    1.31
    atism
    1.30
    ati
    1.29
    Activations Density 0.016%

    No Known Activations