INDEX

Explanations

mentions of work hours or time-related constraints

oai_token-act-pair · gpt-3.5-turbo

phrases related to hours of work or time commitment

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dinand

-0.90

LECT

-0.80

ften

-0.74

esan

-0.74

xual

-0.69

emort

-0.69

reth

-0.68

bard

-0.67

founded

-0.67

raviolet

-0.66

POSITIVE LOGITS

glass

1.15

Ago

0.86

 ILCS

0.82

endment

0.77

urst

0.74

 logged

0.74

 elapsed

0.70

mith

0.70

Hours

0.68

 commute

0.67

Activations Density 0.048%

mentions of work hours or time-related constraints

phrases related to hours of work or time commitment

No Comments

No Known Activations