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. 22525
    Prev
    Next
    INDEX
    Explanations

    terms related to investigations and potential collusion between the Trump campaign and Russia

    oai_token-act-pair · gpt-3.5-turbo

    references to the Trump campaign and its associated figures

    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
    é¾įå
    -0.97
    NetMessage
    -0.88
    Thom
    -0.85
     Ambro
    -0.80
    ONES
    -0.80
    CHAPTER
    -0.80
    REG
    -0.77
    ENGTH
    -0.75
     ILCS
    -0.73
    Ir
    -0.72
    POSITIVE LOGITS
    ossier
    0.86
     hires
    0.82
     chairman
    0.76
    anchester
    0.75
     playbook
    0.75
     adviser
    0.75
     confid
    0.74
     retweet
    0.71
    ilion
    0.71
     pupp
    0.71
    Activations Density 0.121%

    No Known Activations