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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 14161
    Prev
    Next
    INDEX
    Explanations

    instances where a special character "âĢ" is present

    oai_token-act-pair · gpt-3.5-turbo

    emphasis on a particular point or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.78
     lodging
    -0.70
     scatter
    -0.67
     Golem
    -0.63
     Izan
    -0.60
     minim
    -0.60
    isode
    -0.58
     Libyan
    -0.58
     retreat
    -0.58
     recorder
    -0.57
    POSITIVE LOGITS
    £
    1.11
    ¹
    1.03
    Ĵ
    0.97
    ¡
    0.96
    ı
    0.95
    į
    0.94
    »
    0.92
    ®
    0.91
    º
    0.90
    Ī
    0.90
    Activations Density 0.394%

    No Known Activations