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

    Neuronpedia

    Jacobian LensNEW
    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. 4759
    Prev
    Next
    INDEX
    Explanations

    details related to personal experiences or events

    oai_token-act-pair · gpt-3.5-turbo

    content related to personal experiences and relationships

    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
     Hezbollah
    -0.80
     criminal
    -0.76
     elector
    -0.70
     Prosecut
    -0.67
     Shiite
    -0.67
     deterrence
    -0.65
     terrorism
    -0.65
     damages
    -0.65
     ISIL
    -0.64
    lihood
    -0.63
    POSITIVE LOGITS
    nesday
    0.93
    igslist
    0.91
     myself
    0.83
    FTWARE
    0.79
     haha
    0.77
     my
    0.75
    cember
    0.72
    aturdays
    0.71
     comr
    0.70
    Insp
    0.69
    Activations Density 1.972%

    No Known Activations