© 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. 6-RES-JB
    11. 18420
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the impact or influence of actions or events on individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the effects or consequences of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bow
    -0.70
    cele
    -0.64
    majority
    -0.61
    ilings
    -0.61
    mage
    -0.58
    ban
    -0.58
     Ce
    -0.58
    bill
    -0.57
     forthcoming
    -0.57
    guide
    -0.57
    POSITIVE LOGITS
     raining
    0.86
     tremend
    0.77
    bnb
    0.76
     alot
    0.73
     easier
    0.69
     CTR
    0.68
    chwitz
    0.66
     doub
    0.65
    ometimes
    0.63
     interesting
    0.63
    Activations Density 0.222%

    No Known Activations