© 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. 1506
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "As" followed by a capitalized word

    oai_token-act-pair · gpt-3.5-turbo

    the presence of isolated or non-interactive segments in text

    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
    ãģ®å®
    -0.68
    osc
    -0.67
    ||||
    -0.61
    Ùĩ
    -0.61
    ãģł
    -0.59
    pez
    -0.59
     اÙĦ
    -0.57
    scope
    -0.57
     Ùħ
    -0.56
    Ø©
    -0.56
    POSITIVE LOGITS
    piring
    1.42
    bestos
    1.39
    semb
    1.37
    phalt
    1.28
    pects
    1.28
    ymm
    1.20
    ynchronous
    1.17
    piration
    1.17
    leep
    1.15
    semble
    1.14
    Activations Density 0.070%

    No Known Activations