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. 3-RES-JB
    6. 8405
    Prev
    Next
    INDEX
    Explanations

    instances of the word "video" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to video content and multimedia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifts
    -0.76
    uliffe
    -0.72
    thritis
    -0.70
    ichick
    -0.69
    places
    -0.69
    lasting
    -0.68
    izabeth
    -0.67
     intest
    -0.66
    ammad
    -0.65
    sett
    -0.65
    POSITIVE LOGITS
     Vide
    1.14
     Vid
    0.92
     vide
    0.84
    Video
    0.75
     Video
    0.72
    Sav
    0.71
     Zin
    0.71
    uo
    0.69
    ographers
    0.69
     Chat
    0.68
    Activations Density 0.011%

    No Known Activations