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. 4022
    Prev
    Next
    INDEX
    Explanations

    mentions of local government entities like cities and counties

    oai_token-act-pair · gpt-3.5-turbo

    references to urban or city-related topics

    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
    thora
    -0.89
    uble
    -0.87
    issan
    -0.81
    linger
    -0.81
    eful
    -0.80
    uckland
    -0.80
    aler
    -0.79
    ipel
    -0.79
     Carbuncle
    -0.79
    lihood
    -0.78
    POSITIVE LOGITS
     officials
    1.22
     agencies
    1.08
     insiders
    0.98
     staffers
    0.96
     offices
    0.95
     administrators
    0.94
     departments
    0.93
     priorities
    0.93
     authorities
    0.92
     discretion
    0.92
    Activations Density 0.291%

    No Known Activations