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. 3096
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Spain" or things related to Spanish culture

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Spanish" and "Spain"

    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
    ĸļ
    -1.08
    ertodd
    -1.00
    olulu
    -0.96
    mble
    -0.95
    oscope
    -0.94
    ochond
    -0.84
    ritic
    -0.84
    algia
    -0.82
    ostics
    -0.80
    gling
    -0.80
    POSITIVE LOGITS
     Inquisition
    1.36
     Fork
    0.86
     Nieto
    0.84
     jails
    0.79
     Libre
    0.77
     Rican
    0.76
     Rico
    0.74
     unification
    0.70
    wings
    0.70
     pes
    0.70
    Activations Density 0.015%

    No Known Activations