© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 20466
    Prev
    Next
    INDEX
    Explanations

    phrases indicating encountering or facing difficulties or challenges

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "run into."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ģĸ
    -0.86
    Premium
    -0.79
    mort
    -0.75
    arily
    -0.71
    burgh
    -0.69
    export
    -0.69
    oyer
    -0.69
    iew
    -0.68
    iar
    -0.68
    caster
    -0.67
    POSITIVE LOGITS
     trouble
    1.40
     difficulties
    1.26
     problems
    1.20
     obstacles
    1.13
     pitfalls
    1.00
     contradictions
    0.96
     situations
    0.96
     difficulty
    0.95
     adversity
    0.93
     hurdles
    0.91
    Activations Density 0.078%

    No Known Activations