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. 11-RES-JB
    6. 10423
    Prev
    Next
    INDEX
    Explanations

    words related to technology and software

    oai_token-act-pair · gpt-3.5-turbo

    key characteristics and features of devices or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idents
    -0.92
    asions
    -0.86
    lees
    -0.85
    views
    -0.82
    sections
    -0.78
    Rules
    -0.78
    scenes
    -0.77
    eston
    -0.74
    ahs
    -0.74
    76561
    -0.74
    POSITIVE LOGITS
     viable
    1.31
     contender
    1.28
     scalable
    1.24
     competitor
    1.21
     breakthrough
    1.16
     successor
    1.14
     savior
    1.14
     revolutionary
    1.12
     disruptive
    1.09
     challenger
    1.07
    Activations Density 0.241%

    No Known Activations