© 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. 3-RES-JB
    11. 23772
    Prev
    Next
    INDEX
    Explanations

    mention of behaviors or issues related to driving and road usage

    oai_token-act-pair · gpt-3.5-turbo

    terms related to motorists and drivers in traffic contexts

    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
    ibaba
    -0.72
    FORE
    -0.70
     srfAttach
    -0.68
    ASED
    -0.64
    ihara
    -0.63
     Virus
    -0.62
    Aw
    -0.62
     Cere
    -0.62
     Guru
    -0.60
    Pie
    -0.60
    POSITIVE LOGITS
    paces
    0.96
    hip
    0.88
     motorists
    0.88
     beware
    0.85
    afety
    0.84
    aurus
    0.82
    folk
    0.81
     err
    0.78
     accustomed
    0.77
    hips
    0.77
    Activations Density 0.030%

    No Known Activations