© 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. 7059
    Prev
    Next
    INDEX
    Explanations

    words related to difficult situations or challenges

    oai_token-act-pair · gpt-3.5-turbo

    references to suffering or difficult situations

    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
    tein
    -0.79
     nucle
    -0.70
    rotein
    -0.66
    glomer
    -0.65
    ocular
    -0.64
    cium
    -0.63
     pores
    -0.63
     explosives
    -0.62
    encers
    -0.61
    zyme
    -0.61
    POSITIVE LOGITS
     plight
    1.02
    oire
    0.75
    retched
    0.72
    enance
    0.71
    stadt
    0.71
    iless
    0.71
     havoc
    0.69
    cape
    0.69
     Lazarus
    0.69
     endured
    0.67
    Activations Density 0.029%

    No Known Activations