Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 7588
    Prev
    Next
    INDEX
    Explanations

    phrases related to messages or communication

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to communication and messaging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advant
    -0.79
    allery
    -0.75
    iencies
    -0.74
     renovation
    -0.70
    OVA
    -0.70
     contrace
    -0.69
     Timeline
    -0.69
    cul
    -0.68
     renovations
    -0.68
     accommodations
    -0.68
    POSITIVE LOGITS
     uttered
    1.63
     echoed
    1.34
     chanted
    1.26
     conveyed
    1.26
     sung
    1.22
     ringing
    1.21
     echoing
    1.20
     delivered
    1.19
     spoken
    1.18
     preached
    1.18
    Activations Density 0.386%

    No Known Activations