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. 15865
    Prev
    Next
    INDEX
    Explanations

    words related to inquiries and investigations

    oai_token-act-pair · gpt-3.5-turbo

    words related to inquiries or investigations

    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
    enburg
    -0.62
     Depend
    -0.61
    stead
    -0.61
     Beet
    -0.61
    har
    -0.60
    birth
    -0.59
    liners
    -0.58
    alone
    -0.58
     Accord
    -0.57
    éĹĺ
    -0.57
    POSITIVE LOGITS
     probing
    1.10
     inquire
    1.09
     inqu
    1.05
    naires
    1.04
    iry
    1.02
    iries
    0.99
    isition
    0.99
     into
    0.96
     questions
    0.94
    into
    0.89
    Activations Density 0.066%

    No Known Activations