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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5533
    Prev
    Next
    INDEX
    Explanations

    websites or videos related to news events

    oai_token-act-pair · gpt-3.5-turbo

    references to video content in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heit
    -1.00
     laure
    -0.91
    ahime
    -0.89
     Pact
    -0.75
    luster
    -0.73
    oleon
    -0.72
     pact
    -0.70
    wit
    -0.69
    ãĤ¦ãĤ¹
    -0.68
    ktop
    -0.67
    POSITIVE LOGITS
     Videos
    0.95
     Youtube
    0.94
     youtube
    0.92
     videos
    0.92
     uploaded
    0.92
     YouTube
    0.91
    YouTube
    0.89
     Video
    0.88
    accompanied
    0.88
    ideos
    0.87
    Activations Density 0.251%

    No Known Activations