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. 20995
    Prev
    Next
    INDEX
    Explanations

    natural disasters related to extreme weather conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to typhoons and associated terms

    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
    lich
    -0.81
    ername
    -0.76
     WI
    -0.72
    orse
    -0.69
     handshake
    -0.69
    omes
    -0.67
    lig
    -0.67
    eer
    -0.66
    nesota
    -0.66
     Root
    -0.65
    POSITIVE LOGITS
    oons
    0.90
    inx
    0.83
    onte
    0.79
    oulos
    0.70
    tro
    0.69
    ijn
    0.69
     antid
    0.66
    mos
    0.65
    oon
    0.63
     gastro
    0.63
    Activations Density 0.052%

    No Known Activations