© 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. 0-RES-JB
    6. 1438
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges or difficulties, especially in overcoming obstacles

    oai_token-act-pair · gpt-3.5-turbo

    references to challenges or barriers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âĸĪ
    -0.67
    seys
    -0.64
    edo
    -0.63
    caster
    -0.63
     Paste
    -0.60
     Lol
    -0.60
     dated
    -0.60
    weet
    -0.60
    cus
    -0.59
     Chronicles
    -0.58
    POSITIVE LOGITS
     obstacles
    3.55
     obstacle
    3.11
     hurdles
    2.95
     barriers
    2.47
     hurdle
    2.37
     imped
    2.20
     Obst
    1.75
     setbacks
    1.70
     barrier
    1.57
     challenges
    1.52
    Activations Density 0.031%

    No Known Activations