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. 12663
    Prev
    Next
    INDEX
    Explanations

    mentions of legislative or governmental actions and procedures

    oai_token-act-pair · gpt-3.5-turbo

    the frequent use of the word "the" in sentences

    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
     whilst
    -0.74
     besides
    -0.73
    !!!!
    -0.71
    !!!
    -0.71
    \'
    -0.69
    =""
    -0.68
    adoes
    -0.66
    ibl
    -0.66
    Layer
    -0.65
    lime
    -0.65
    POSITIVE LOGITS
     latter
    1.17
     nation
    1.13
     country
    1.12
     latest
    1.11
     Kremlin
    1.06
     same
    1.05
     president
    1.02
    ocratic
    1.01
     United
    0.98
    resa
    0.95
    Activations Density 1.315%

    No Known Activations