© 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. 7232
    Prev
    Next
    INDEX
    Explanations

    words related to financial or economic struggles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "struggling" 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
    opl
    -0.85
    osate
    -0.83
    alog
    -0.80
    oho
    -0.79
    othy
    -0.79
    chu
    -0.77
    cision
    -0.74
    roma
    -0.73
    tein
    -0.73
    ific
    -0.72
    POSITIVE LOGITS
     struggling
    0.79
     Stru
    0.77
     miser
    0.75
     orphans
    0.72
    NESS
    0.70
     strugg
    0.67
     Squid
    0.67
     facing
    0.66
     reeling
    0.64
     Solitaire
    0.63
    Activations Density 0.021%

    No Known Activations