INDEX

Explanations

words related to time and waiting

oai_token-act-pair · gpt-3.5-turbo

terms related to time efficiency and duration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

unin

-0.89

riad

-0.86

irie

-0.77

uthor

-0.74

rim

-0.72

ĳå£«

-0.71

osher

-0.69

geries

-0.69

ramid

-0.68

tical

-0.68

POSITIVE LOGITS

frames

1.11

 elapsed

1.06

 periods

1.05

 interval

0.94

 expectancy

0.91

 continuum

0.91

 period

0.91

 delay

0.89

duration

0.88

 intervals

0.87

Activations Density 0.126%

words related to time and waiting

terms related to time efficiency and duration

No Comments

No Known Activations