© 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. 1578
    Prev
    Next
    INDEX
    Explanations

    phrases related to causing actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating various types of disruptions or negative impacts

    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
    chens
    -0.80
    uthor
    -0.76
    emouth
    -0.74
     Provided
    -0.72
     Puzzles
    -0.71
    razen
    -0.71
    nesday
    -0.71
    ospels
    -0.70
     Signed
    -0.68
    nis
    -0.68
    POSITIVE LOGITS
     havoc
    1.00
     disturbance
    0.88
     eruption
    0.83
     injury
    0.76
     unnecessary
    0.76
     earthqu
    0.76
     wrath
    0.76
     mayhem
    0.74
     outburst
    0.74
     contamination
    0.74
    Activations Density 0.234%

    No Known Activations