INDEX

Explanations

time-related phrases related to deadlines or remaining time

oai_token-act-pair · gpt-3.5-turbo

references to time remaining or deadlines

oai_token-act-pair · gpt-4o-mini Triggered 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

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cult

-0.84

wcsstore

-0.83

pecially

-0.80

tnc

-0.79

heter

-0.74

usa

-0.72

elled

-0.70

ãĥĻ

-0.69

abuse

-0.68

climate

-0.67

POSITIVE LOGITS

 allotted

0.77

itia

0.74

 unanswered

0.72

akia

0.71

 spare

0.70

 elapsed

0.70

 Empty

0.65

akings

0.64

 left

0.63

SPD

0.62

Activations Density 0.123%

time-related phrases related to deadlines or remaining time

references to time remaining or deadlines

No Comments

No Known Activations