INDEX

Explanations

instances of the phrase "two years ago" in a text

oai_token-act-pair · gpt-3.5-turbo

references to time durations, specifically the phrase "years ago."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Halls

-0.67

ogle

-0.66

ople

-0.66

ibrary

-0.65

 toilet

-0.65

anooga

-0.63

icator

-0.61

 plun

-0.60

 subp

-0.60

own

-0.60

POSITIVE LOGITS

ago

1.49

Ago

1.24

 apiece

1.06

 elapsed

0.88

iversary

0.87

long

0.87

 olds

0.85

izons

0.79

 overdue

0.77

shy

0.75

Activations Density 0.123%

instances of the phrase "two years ago" in a text

references to time durations, specifically the phrase "years ago."

No Comments

No Known Activations