© 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. 3-RES-JB
    11. 15235
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or measures that are necessary or required

    oai_token-act-pair · gpt-3.5-turbo

    the word "necessary" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.80
    uay
    -0.78
    ning
    -0.73
    bow
    -0.72
    gdala
    -0.70
    bour
    -0.69
    mbuds
    -0.67
    naissance
    -0.66
    bish
    -0.66
    rik
    -0.65
    POSITIVE LOGITS
     guiActiveUn
    0.90
     ingredient
    0.85
     introdu
    0.83
     necessities
    0.83
     reinforcements
    0.78
     ingred
    0.74
     precautions
    0.72
     supplies
    0.71
     organs
    0.70
     prerequisite
    0.70
    Activations Density 0.026%

    No Known Activations