© 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. 23680
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    references to challenges or difficulties

    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
    otide
    -0.80
    ahon
    -0.80
    rigan
    -0.71
    umn
    -0.70
    izations
    -0.68
    avia
    -0.68
    azeera
    -0.68
    tarian
    -0.68
    alez
    -0.67
    creen
    -0.66
    POSITIVE LOGITS
     posed
    1.01
    ingly
    0.82
     challenge
    0.77
    ioned
    0.75
    enged
    0.74
    enges
    0.73
     insur
    0.72
     confronting
    0.72
     facing
    0.71
     faced
    0.68
    Activations Density 0.031%

    No Known Activations