© 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. 20545
    Prev
    Next
    INDEX
    Explanations

    phrases related to current events and news updates

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Now" media content

    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
     Berm
    -0.62
     similarity
    -0.60
     resemb
    -0.60
     Parsons
    -0.60
     fault
    -0.59
     similarities
    -0.58
    é¾
    -0.58
     disob
    -0.57
     elim
    -0.57
     Parables
    -0.56
    POSITIVE LOGITS
    adays
    1.53
    here
    1.27
    heres
    1.08
    ledge
    0.85
    ledged
    0.85
     Playing
    0.83
     Launcher
    0.83
    !,
    0.78
    lies
    0.75
    heric
    0.74
    Activations Density 0.027%

    No Known Activations