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. 15159
    Prev
    Next
    INDEX
    Explanations

    instances of the word "need."

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the necessity for something

    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
     Sabb
    -0.62
    theless
    -0.62
     Tit
    -0.55
     mathemat
    -0.55
     GHz
    -0.53
     Bride
    -0.52
     Surv
    -0.51
     Voy
    -0.50
     Seym
    -0.49
     Dreams
    -0.49
    POSITIVE LOGITS
    lessly
    1.29
     for
    0.99
    lest
    0.95
    iness
    0.94
    iest
    0.85
    lessness
    0.82
     to
    0.81
    for
    0.78
    ful
    0.75
    ling
    0.73
    Activations Density 0.043%

    No Known Activations