© 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. 3565
    Prev
    Next
    INDEX
    Explanations

    mentions of different operating systems

    oai_token-act-pair · gpt-3.5-turbo

    mentions of operating systems

    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
    grand
    -0.85
    hur
    -0.78
    aina
    -0.76
    iba
    -0.76
    grave
    -0.74
    irl
    -0.72
    aternal
    -0.72
    uel
    -0.71
    lower
    -0.71
    inas
    -0.70
    POSITIVE LOGITS
     administrator
    0.83
     systems
    0.81
     manuals
    0.81
     Creed
    0.81
    ORPG
    0.78
     sshd
    0.76
     Administrator
    0.74
     correctness
    0.74
     emulator
    0.73
     administrators
    0.72
    Activations Density 0.026%

    No Known Activations