INDEX

Explanations

phrases indicating something happening continuously or consistently throughout a period of time

oai_token-act-pair · gpt-3.5-turbo

the word "throughout."

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

potion

-0.74

elling

-0.71

rets

-0.71

JV

-0.69

LS

-0.68

bol

-0.68

INS

-0.66

hl

-0.66

umo

-0.65

GE

-0.65

POSITIVE LOGITS

eatures

0.79

 disciplines

0.77

 stages

0.77

vironment

0.73

 Europe

0.71

ciating

0.70

 phases

0.69

XD

0.69

 Wage

0.69

ĸļ

0.67

Activations Density 0.018%

phrases indicating something happening continuously or consistently throughout a period of time

the word "throughout."

No Comments

No Known Activations