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. 16376
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal structures and beliefs

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "world" in various contexts

    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
    veyard
    -0.86
     actionGroup
    -0.84
    oug
    -0.78
    ippi
    -0.78
    aturday
    -0.75
    etsk
    -0.74
    ibility
    -0.74
    utenant
    -0.71
    IFF
    -0.71
    odox
    -0.70
    POSITIVE LOGITS
    liness
    0.92
    building
    0.82
    scape
    0.74
    eers
    0.73
     revolves
    0.73
    icz
    0.69
    arium
    0.68
    fare
    0.67
     outlook
    0.66
     economy
    0.65
    Activations Density 0.054%

    No Known Activations