INDEX

Explanations

time-related phrases indicating spans of years

oai_token-act-pair · gpt-3.5-turbo

references to time periods or durations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

owsky

-0.72

aples

-0.65

 Ment

-0.65

oÄŁ

-0.64

gall

-0.62

rox

-0.62

endas

-0.61

hai

-0.61

enh

-0.60

enes

-0.59

POSITIVE LOGITS

brance

0.67

 ASUS

0.64

IAS

0.63

ago

0.60

idia

0.59

,.

0.58

iferation

0.57

!--

0.56

CLE

0.55

opian

0.55

Activations Density 0.095%

time-related phrases indicating spans of years

references to time periods or durations

No Comments

No Known Activations