INDEX

Explanations

time periods and durations

oai_token-act-pair · gpt-3.5-turbo

phrases related to the duration of time or specific periods

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

ply

-0.87

alty

-0.83

alties

-0.81

ilet

-0.75

tty

-0.72

\\\\\\\\

-0.71

square

-0.70

 Tribe

-0.69

deck

-0.67

errilla

-0.67

POSITIVE LOGITS

 periods

0.85

 stagnation

0.84

 Exile

0.81

iatus

0.75

 probation

0.75

 elapsed

0.71

 duration

0.71

 confinement

0.70

 longest

0.69

 timeframe

0.69

Activations Density 0.095%

time periods and durations

phrases related to the duration of time or specific periods

No Comments

No Known Activations