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. 10013
    Prev
    Next
    INDEX
    Explanations

    words related to potential struggles or challenges

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to risk and safety

    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
    20439
    -0.59
     Jury
    -0.57
     Coffin
    -0.53
    osphere
    -0.51
    riot
    -0.51
    uran
    -0.50
    robe
    -0.50
    rome
    -0.49
     subsistence
    -0.49
     Exile
    -0.49
    POSITIVE LOGITS
    fully
    0.82
    lessly
    0.79
     wise
    0.79
    bably
    0.71
    imately
    0.66
    ually
    0.65
    ally
    0.63
     crept
    0.63
    wise
    0.63
     flowed
    0.61
    Activations Density 0.601%

    No Known Activations