INDEX

Explanations

time-related terms, specifically durations like "weeks" and "months"

oai_token-act-pair · gpt-3.5-turbo

references to time periods, particularly focusing on months, weeks, days, and hours

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

llor

-0.87

ICO

-0.70

 charity

-0.69

alach

-0.69

iasis

-0.69

atche

-0.68

onis

-0.68

tarian

-0.67

ribution

-0.65

ocard

-0.64

POSITIVE LOGITS

Zup

0.81

 Seconds

0.78

pread

0.76

peed

0.75

hift

0.75

pring

0.74

 centimeters

0.74

ago

0.73

©¶æ

0.70

Ago

0.68

Activations Density 0.066%

time-related terms, specifically durations like "weeks" and "months"

references to time periods, particularly focusing on months, weeks, days, and hours

No Comments

No Known Activations