INDEX

Explanations

expressions of time durations, particularly involving years and months

oai_token-act-pair · gpt-3.5-turbo

references to durations of time, particularly in years, months, and days

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥķãĤ©

-0.78

erno

-0.70

anooga

-0.68

irie

-0.67

idal

-0.67

Tro

-0.64

rote

-0.64

agonist

-0.64

ãĥĥãĥī

-0.63

liction

-0.62

POSITIVE LOGITS

ago

1.20

 increments

1.02

 olds

1.01

 apiece

0.91

Ago

0.88

 intervals

0.86

 elapsed

0.83

Duration

0.80

 periods

0.80

 onwards

0.77

Activations Density 0.134%

expressions of time durations, particularly involving years and months

references to durations of time, particularly in years, months, and days

No Comments

No Known Activations