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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 23332
    Prev
    Next
    INDEX
    Explanations

    references to a specific telecommunication company named "Sprint."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the brand name "Sprint" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arial
    -0.80
     Kubrick
    -0.71
    epad
    -0.66
    arist
    -0.66
    hunt
    -0.66
    emis
    -0.65
    annis
    -0.64
     fet
    -0.64
    jamin
    -0.63
    âĿ
    -0.63
    POSITIVE LOGITS
    DAQ
    0.83
    Mobile
    0.82
    rats
    0.82
     Sprint
    0.76
     Unlimited
    0.76
    EED
    0.75
     Mobility
    0.71
    SQL
    0.71
    Plus
    0.69
     Wireless
    0.67
    Activations Density 0.004%

    No Known Activations