© 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. 6-RES-JB
    11. 1490
    Prev
    Next
    INDEX
    Explanations

    references to physically acquiring or possessing something

    oai_token-act-pair · gpt-3.5-turbo

    references to acquiring or grasping something, often in a metaphorical sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elig
    -0.68
    ipolar
    -0.59
    amera
    -0.53
     futures
    -0.47
     awa
    -0.47
    ignt
    -0.46
     equals
    -0.45
     glob
    -0.45
     depos
    -0.45
    allo
    -0.44
    POSITIVE LOGITS
    ghai
    0.60
     thereof
    0.53
    rek
    0.52
     Os
    0.50
    lis
    0.49
    ography
    0.48
    UTH
    0.48
    opl
    0.47
     Fang
    0.46
    gha
    0.46
    Activations Density 0.314%

    No Known Activations