© 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. 7-RES-JB
    11. 4393
    Prev
    Next
    INDEX
    Explanations

    words related to challenges, obstacles, or complexities

    oai_token-act-pair · gpt-3.5-turbo

    discussions around the concept of difficulty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.70
    oak
    -0.68
    rum
    -0.68
    ta
    -0.68
    ergy
    -0.67
    gling
    -0.67
    eer
    -0.65
    eve
    -0.64
    roup
    -0.63
    ovies
    -0.62
    POSITIVE LOGITS
    iculty
    0.93
    ioned
    0.88
    hooting
    0.85
    olving
    0.80
    icult
    0.79
    QUI
    0.71
     impede
    0.69
     Flavoring
    0.68
    Reply
    0.68
    awaru
    0.68
    Activations Density 0.040%

    No Known Activations