Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 23788
    Prev
    Next
    INDEX
    Explanations

    financial terms and references to ratings agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to the organization "Standard & Poor's."

    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
    76561
    -0.75
    cig
    -0.75
     destro
    -0.73
    resent
    -0.70
    hig
    -0.68
    senal
    -0.66
    cffffcc
    -0.66
     wart
    -0.66
    Unknown
    -0.65
    shit
    -0.64
    POSITIVE LOGITS
     deviation
    1.11
     deviations
    1.01
     Catalog
    0.82
     Chart
    0.81
    ization
    0.80
    ised
    0.77
     Definition
    0.77
    ity
    0.76
     Format
    0.76
     Template
    0.74
    Activations Density 0.011%

    No Known Activations