INDEX

Explanations

the abbreviation 'NDP'

oai_token-act-pair · gpt-3.5-turbo

mentions of the NDP (New Democratic Party)

oai_token-act-pair · gpt-4o-mini

Triggered 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

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

zona

-0.86

ãĤ·ãĥ£

-0.81

inventoryQuantity

-0.79

 Dull

-0.75

ocity

-0.74

 McCoy

-0.74

 Ragnarok

-0.72

ooter

-0.70

tes

-0.70

ordon

-0.70

POSITIVE LOGITS

NDP

0.99

 Opposition

0.77

 insurgency

0.75

 Liberals

0.73

 leadership

0.73

 treasury

0.72

 provincial

0.72

 Provincial

0.71

LAB

0.71

 stronghold

0.70

Activations Density 0.010%

the abbreviation 'NDP'

mentions of the NDP (New Democratic Party)

No Known Activations