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. 9-RES-JB
    6. 12511
    Prev
    Next
    INDEX
    Explanations

    contractions of 'could not' or 'would not'

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing emotions, particularly happiness and excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     periodically
    -0.63
     migrate
    -0.60
     converge
    -0.59
     smugg
    -0.59
     recept
    -0.59
     sanity
    -0.59
    yip
    -0.59
     gradually
    -0.59
    alian
    -0.58
     someday
    -0.58
    POSITIVE LOGITS
    inventoryQuantity
    0.70
    abby
    0.66
     understatement
    0.61
    ł
    0.60
    efe
    0.60
    taboola
    0.60
    Ì
    0.59
    Į
    0.59
    uttered
    0.59
    eve
    0.59
    Activations Density 0.338%

    No Known Activations