© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 11931
    Prev
    Next
    INDEX
    Explanations

    adjectives describing disorder or confusion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chaos and disorder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iphate
    -0.87
    href
    -0.78
    fighter
    -0.76
    atum
    -0.75
    plane
    -0.75
    haps
    -0.74
    alach
    -0.73
    inet
    -0.73
    ngth
    -0.72
    arations
    -0.72
    POSITIVE LOGITS
     chaotic
    0.87
     adolesc
    0.87
     affairs
    0.85
     combust
    0.84
     atmosp
    0.81
     scenes
    0.75
     times
    0.74
     multip
    0.73
     waters
    0.73
     aspects
    0.72
    Activations Density 0.034%

    No Known Activations