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. 9-RES-JB
    6. 12831
    Prev
    Next
    INDEX
    Explanations

    phrases related to time, return, and comparison

    oai_token-act-pair · gpt-3.5-turbo

    references to trends in market performance or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oS
    -0.64
    ogo
    -0.59
    amina
    -0.59
    ello
    -0.58
    robe
    -0.58
    Frameworks
    -0.58
    ema
    -0.57
    strip
    -0.57
    mega
    -0.56
    osi
    -0.55
    POSITIVE LOGITS
     previous
    1.37
     old
    1.27
     previously
    1.23
     predecessors
    1.21
     past
    1.21
     formerly
    1.18
     original
    1.14
     predecessor
    1.10
    gone
    1.10
     Previously
    1.08
    Activations Density 1.345%

    No Known Activations