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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 3360
    Prev
    Next
    INDEX
    Explanations

    words related to waste management and cleanliness

    oai_token-act-pair · gpt-3.5-turbo

    references to waste and garbage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saf
    -0.81
    akening
    -0.78
    ym
    -0.77
    ffield
    -0.76
    ationally
    -0.75
    knit
    -0.74
    orney
    -0.74
    hip
    -0.73
    ghai
    -0.73
    metic
    -0.73
    POSITIVE LOGITS
     garbage
    1.10
     dumps
    1.02
     cans
    0.92
    bage
    0.92
     inciner
    0.91
     disposal
    0.90
     bags
    0.88
     heap
    0.86
     dump
    0.85
     collector
    0.83
    Activations Density 0.005%

    No Known Activations