© 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. 4-RES-JB
    11. 17372
    Prev
    Next
    INDEX
    Explanations

    mentions of the technology company Samsung

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand Samsung

    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
    orget
    -0.86
    umbn
    -0.74
    ãĥĥãĥĪ
    -0.74
    ablishment
    -0.74
    asure
    -0.72
    wild
    -0.69
    avez
    -0.66
    ebin
    -0.66
    juries
    -0.65
    ownt
    -0.63
    POSITIVE LOGITS
     Electronics
    1.14
     Galaxy
    1.01
    Samsung
    1.01
     Samsung
    0.85
    amsung
    0.82
    SQL
    0.82
    ites
    0.79
    Mobile
    0.77
    itic
    0.74
    ITE
    0.74
    Activations Density 0.005%

    No Known Activations