© 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. 22454
    Prev
    Next
    INDEX
    Explanations

    phrases related to corruption in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of corruption

    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
    UNCH
    -0.79
    ynthesis
    -0.74
     Anxiety
    -0.74
    TRY
    -0.72
    gain
    -0.72
    iphate
    -0.71
    WAYS
    -0.70
    arten
    -0.70
    gat
    -0.68
    Demand
    -0.67
    POSITIVE LOGITS
     corrupt
    0.96
    ible
    0.93
    ions
    0.86
    ingly
    0.85
     undermin
    0.80
    ly
    0.79
     dealings
    0.78
     corruption
    0.78
    ibly
    0.78
     corrupted
    0.76
    Activations Density 0.011%

    No Known Activations