© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 4468
    Prev
    Next
    INDEX
    Explanations

    internet speed measurements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to internet bandwidth and speeds

    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
    gren
    -0.74
    oras
    -0.68
    arist
    -0.68
    rums
    -0.67
    orical
    -0.67
    orically
    -0.64
    rine
    -0.64
    atorial
    -0.64
    onia
    -0.64
    neys
    -0.63
    POSITIVE LOGITS
     Mbps
    1.07
    Mbps
    1.02
    bps
    0.97
    fen
    0.75
    Upload
    0.71
    ruary
    0.70
     Rates
    0.70
    glas
    0.69
     speeds
    0.69
    _.
    0.68
    Activations Density 0.008%

    No Known Activations