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. 13687
    Prev
    Next
    INDEX
    Explanations

    names related to the subject "Lazar" or locations related to the subject "Hazar" **(Note: The complete ending is likely "Hazaratbal")**

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities associated with the name "Laz" or "Haz."

    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
    etheless
    -0.93
    ĨĴ
    -0.85
    vironment
    -0.81
    ļéĨĴ
    -0.74
    ¶ħ
    -0.72
    ¥ŀ
    -0.71
    iscopal
    -0.68
     peninsula
    -0.67
     fixme
    -0.66
    CLASSIFIED
    -0.66
    POSITIVE LOGITS
    hou
    1.22
    arette
    1.05
    arro
    0.97
    arettes
    0.97
    mat
    0.89
    arre
    0.88
    ett
    0.85
    etta
    0.83
    busters
    0.83
    rael
    0.82
    Activations Density 0.020%

    No Known Activations