© 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. 9-RES-JB
    11. 13535
    Prev
    Next
    INDEX
    Explanations

    verbs related to overcoming obstacles or challenges

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to overcoming challenges or obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cas
    -0.85
    psc
    -0.84
    dot
    -0.82
    asus
    -0.79
    hyde
    -0.76
    spot
    -0.73
    dar
    -0.72
    cam
    -0.71
    overe
    -0.71
    gas
    -0.71
    POSITIVE LOGITS
     obstacles
    1.49
     adversity
    1.45
     difficulties
    1.25
     hurdles
    1.25
     barriers
    1.10
     hardships
    1.08
     hurdle
    1.08
     weaknesses
    1.07
     obstacle
    1.06
     insur
    1.05
    Activations Density 0.064%

    No Known Activations