INDEX

Explanations

phrases related to time duration

oai_token-act-pair · gpt-3.5-turbo

phrases that reference the passage of time, specifically in relation to the last several years or decades

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

ollow

-0.71

aband

-0.70

hots

-0.65

udd

-0.65

acers

-0.64

obs

-0.64

athing

-0.64

ingen

-0.63

afort

-0.63

mbuds

-0.63

POSITIVE LOGITS

decade

1.15

 ditch

0.97

 gasp

0.95

 millennium

0.94

 month

0.94

ebin

0.91

 week

0.90

 year

0.89

 century

0.88

 installment

0.88

Activations Density 0.032%

phrases related to time duration

phrases that reference the passage of time, specifically in relation to the last several years or decades

No Comments

No Known Activations