© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 8387
    Prev
    Next
    INDEX
    Explanations

    a specific word or term that ends with 'ched', such as 'scheduled' or 'reached'

    oai_token-act-pair · gpt-3.5-turbo

    words related to observation or noticing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.88
    DragonMagazine
    -0.70
     correctional
    -0.67
    dylib
    -0.65
    atively
    -0.65
     Barclays
    -0.65
    iquid
    -0.63
    enhagen
    -0.62
    DOS
    -0.62
    inals
    -0.62
    POSITIVE LOGITS
    uled
    1.05
    ched
    0.89
    ches
    0.88
    bones
    0.83
    uling
    0.83
    lish
    0.83
    laus
    0.81
    uler
    0.80
    bone
    0.79
    weet
    0.77
    Activations Density 0.016%

    No Known Activations