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. 8417
    Prev
    Next
    INDEX
    Explanations

    key-value pairs in a data structure with specific identifiers

    oai_token-act-pair · gpt-3.5-turbo

    identifiers and properties in structured data formats, likely related to databases or programming

    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
    dinand
    -0.81
    GoldMagikarp
    -0.79
    atre
    -0.78
    Reilly
    -0.75
    issance
    -0.75
    onna
    -0.74
    hett
    -0.74
    ridor
    -0.74
    estones
    -0.74
    ixel
    -0.74
    POSITIVE LOGITS
     nil
    0.94
    hover
    0.86
     undefined
    0.85
     {}
    0.78
     null
    0.78
     unspecified
    0.77
    flags
    0.76
     NULL
    0.74
     Unknown
    0.74
     fmt
    0.73
    Activations Density 0.041%

    No Known Activations