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. 22033
    Prev
    Next
    INDEX
    Explanations

    phrases indicating physical position or movement over something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "over."

    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
    illary
    -0.88
    ¯¯¯¯
    -0.73
    UE
    -0.72
     Lauder
    -0.71
    uum
    -0.65
    arium
    -0.64
    UES
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.62
    ãĥ¼ãĥĨ
    -0.60
    egal
    -0.60
    POSITIVE LOGITS
    hang
    1.11
    loading
    1.01
    drive
    0.97
    tones
    0.95
    lord
    0.93
    lay
    0.92
    hung
    0.87
    haul
    0.84
    kill
    0.83
    mast
    0.83
    Activations Density 0.081%

    No Known Activations