© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 24334
    Prev
    Next
    INDEX
    Explanations

    phrases related to data collection, intelligence gathering, and territorial control

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to intelligence, data collection, and financial transactions

    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
     Hitch
    -0.64
     Lesbian
    -0.63
    ovie
    -0.60
    itsch
    -0.58
     Pats
    -0.57
    joining
    -0.54
     Ladies
    -0.52
     Dy
    -0.52
     Myr
    -0.51
     studied
    -0.50
    POSITIVE LOGITS
    aram
    0.80
    ifully
    0.72
     abroad
    0.70
    ilaterally
    0.70
    matically
    0.69
     everywhere
    0.65
     onstage
    0.63
     backstage
    0.63
    afety
    0.62
     anew
    0.62
    Activations Density 0.613%

    No Known Activations