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. 2-RES-JB
    6. 8594
    Prev
    Next
    INDEX
    Explanations

    terms related to the appearance or sudden introduction of new concepts, ideas, or entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to emergence and disappearance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rote
    -0.69
    atomic
    -0.66
    geon
    -0.65
    cell
    -0.62
    roph
    -0.61
     Hollow
    -0.61
    bread
    -0.61
     subdiv
    -0.60
     fluorescent
    -0.60
     saline
    -0.60
    POSITIVE LOGITS
     Awareness
    0.87
     thereof
    0.85
    uation
    0.84
    jriwal
    0.82
    uality
    0.81
     occurrence
    0.80
    dates
    0.78
    anguage
    0.78
     Takeru
    0.77
     emergence
    0.76
    Activations Density 0.058%

    No Known Activations