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. 11714
    Prev
    Next
    INDEX
    Explanations

    phrases related to automobile components and operations, such as door seals, driver's licenses, and safety systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and driving 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
    jri
    -0.83
    yip
    -0.79
    achus
    -0.77
    iland
    -0.75
    urat
    -0.73
    ibaba
    -0.70
     grapes
    -0.68
    soType
    -0.67
    ashtra
    -0.67
    phrine
    -0.66
    POSITIVE LOGITS
    command
    0.79
    operated
    0.75
    execute
    0.74
    Command
    0.71
    ij士
    0.67
     Commands
    0.67
    Cmd
    0.67
     command
    0.66
    BILITIES
    0.64
     remotely
    0.64
    Activations Density 0.672%

    No Known Activations