Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 4985
    Prev
    Next
    INDEX
    Explanations

    phrases related to building, creating, or establishing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to building, growth, or development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seek
    -0.81
    stretched
    -0.74
    Ö¼
    -0.72
    edi
    -0.68
    otiation
    -0.64
    jee
    -0.64
    blank
    -0.62
    zzle
    -0.62
    BUS
    -0.62
    fy
    -0.61
    POSITIVE LOGITS
     groundwork
    0.82
     infrastructure
    0.69
     Habit
    0.68
     semic
    0.67
     fences
    0.66
     capability
    0.66
    wagen
    0.65
     footh
    0.64
     niche
    0.64
     foundations
    0.63
    Activations Density 0.241%

    No Known Activations