© 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. 3-RES-JB
    11. 23312
    Prev
    Next
    INDEX
    Explanations

    expressions related to political and social struggles

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of struggle in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omin
    -0.78
    ħĭ
    -0.69
    orm
    -0.69
    ĻĤ
    -0.68
    collar
    -0.65
    olk
    -0.65
    Male
    -0.64
    repl
    -0.64
    redit
    -0.64
    orc
    -0.64
    POSITIVE LOGITS
     Struggle
    1.16
     struggle
    0.88
     Sioux
    0.84
     against
    0.80
     struggles
    0.76
     cry
    0.75
     toward
    0.69
     towards
    0.69
     confronting
    0.68
     Hunger
    0.68
    Activations Density 0.020%

    No Known Activations