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. 7-RES-JB
    6. 23000
    Prev
    Next
    INDEX
    Explanations

    mentions of privacy-related issues or terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to privacy policies and notices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uana
    -0.74
    pires
    -0.71
     coord
    -0.67
    Js
    -0.62
    iov
    -0.60
    ammy
    -0.60
    reek
    -0.60
    icion
    -0.59
     prototyp
    -0.59
     Dynam
    -0.58
    POSITIVE LOGITS
    ylon
    0.69
    irmation
    0.68
    ificate
    0.67
     alerts
    0.65
     Spotify
    0.64
    Privacy
    0.63
     expired
    0.63
     Submit
    0.62
     Newsletter
    0.62
    anty
    0.61
    Activations Density 0.012%

    No Known Activations