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. 12633
    Prev
    Next
    INDEX
    Explanations

    references to electronic devices or locations related to technology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of mobile devices and related technology

    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
     legacy
    -0.65
     Destination
    -0.62
     workflow
    -0.61
     enterprise
    -0.60
     Ãľ
    -0.60
     Maxwell
    -0.60
     Origin
    -0.59
    Content
    -0.58
    Interface
    -0.58
     Analog
    -0.58
    POSITIVE LOGITS
    bol
    0.88
    aton
    0.77
    ioned
    0.75
    agogue
    0.74
    anus
    0.72
    ertain
    0.72
    osa
    0.71
    anches
    0.71
    hens
    0.71
    arak
    0.70
    Activations Density 0.522%

    No Known Activations