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. 4-RES-JB
    6. 18719
    Prev
    Next
    INDEX
    Explanations

    phrases where the word "as" is used to draw a comparison or introduce a reason

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "as" in various contexts

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

    No Comments

    Negative Logits
    OUR
    -0.74
    âĹ¼
    -0.72
    Reply
    -0.68
    Gear
    -0.67
    Enlarge
    -0.66
    Sharp
    -0.65
    Rub
    -0.63
    Subscribe
    -0.63
    ainer
    -0.63
    roads
    -0.60
    POSITIVE LOGITS
     evidenced
    1.27
    bestos
    1.12
    semb
    1.08
     opposed
    1.02
    pired
    0.99
    phy
    0.98
    semble
    0.95
    piring
    0.94
    piration
    0.92
     well
    0.90
    Activations Density 0.086%

    No Known Activations