INDEX

Explanations

time-related words and phrases, specifically focusing on durations such as years and months

oai_token-act-pair · gpt-3.5-turbo

references to time durations, specifically years and months

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

acus

-0.76

emale

-0.75

liction

-0.73

acted

-0.72

nels

-0.70

Reviewer

-0.70

obook

-0.67

ocaly

-0.67

ople

-0.65

ococ

-0.64

POSITIVE LOGITS

ago

1.38

Ago

1.33

 elapsed

0.97

 later

0.96

shy

0.90

 Later

0.88

 ahead

0.87

 Ahead

0.85

 transpired

0.80

 hindsight

0.79

Activations Density 0.084%

time-related words and phrases, specifically focusing on durations such as years and months

references to time durations, specifically years and months

No Comments

No Known Activations