© 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. 1-RES-JB
    11. 18634
    Prev
    Next
    INDEX
    Explanations

    mentions of the specific name "Blum," with a higher activation value for "Blum" emphasized

    oai_token-act-pair · gpt-3.5-turbo

    the name "Blum" or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cutoff
    -0.74
     Aires
    -0.72
    Ń·
    -0.69
     Cosponsors
    -0.68
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.67
     deserts
    -0.67
     Attribution
    -0.66
    ;;;;;;;;;;;;
    -0.64
     Shades
    -0.64
    ãĥ¼ãĤ¯
    -0.62
    POSITIVE LOGITS
    um
    1.12
    osity
    1.06
    mers
    1.03
    essage
    0.95
    mary
    0.94
    pty
    0.93
    atsu
    0.92
    etric
    0.91
    ouse
    0.91
    munition
    0.91
    Activations Density 0.015%

    No Known Activations