© 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. 10-RES-JB
    11. 16126
    Prev
    Next
    INDEX
    Explanations

    phrases related to news reporting

    oai_token-act-pair · gpt-3.5-turbo

    references to authoritative sources or reports in news articles

    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
    Plex
    -0.75
     Toast
    -0.74
    uggle
    -0.67
     Saturdays
    -0.64
    ;;;;;;;;;;;;
    -0.64
     circa
    -0.61
    âĶĢâĶĢâĶĢâĶĢ
    -0.60
    locks
    -0.60
    abouts
    -0.58
    cheat
    -0.58
    POSITIVE LOGITS
     noted
    1.33
     cited
    1.32
     cautioned
    1.25
     stated
    1.24
     warned
    1.23
     added
    1.22
     stressed
    1.21
     emphasized
    1.20
     emphas
    1.20
     urged
    1.20
    Activations Density 0.291%

    No Known Activations