INDEX

Explanations

government-related terms and discussions about policy impact

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att_32k-oai

Configuration

jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

32,768

Data Type

torch.float32

Hook Name

blocks.3.hook_attn_out

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BuyableInstoreAndOnline

-0.87

inventoryQuantity

-0.82

senal

-0.76

²¾

-0.74

 advoc

-0.69

 Canaver

-0.68

hog

-0.67

kef

-0.65

DonaldTrump

-0.65

imaru

-0.65

POSITIVE LOGITS

thirds

0.66

 satisfies

0.63

 joins

0.61

uctive

0.61

puted

0.61

 authenticated

0.60

balanced

0.60

mission

0.60

ittal

0.57

cedented

0.57

Activations Density 0.210%

government-related terms and discussions about policy impact

No Comments

No Known Activations