© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4512
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and security breaches

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    information concerning security breaches and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     envision
    -0.74
     canoe
    -0.68
    puff
    -0.68
    MJ
    -0.68
     Agenda
    -0.67
     airst
    -0.67
     dope
    -0.66
    PRES
    -0.66
     1961
    -0.65
     exh
    -0.65
    POSITIVE LOGITS
     outage
    1.55
    ifax
    1.12
     downtime
    1.09
     refunds
    1.07
     breach
    1.07
    ffect
    1.07
     hackers
    1.07
     iCloud
    1.05
     affected
    1.04
     ransomware
    1.03
    Activations Density 0.692%

    No Known Activations