INDEX

Explanations

places or points where something, such as a schedule, journey, event, or process, comes to a halt or a designated end

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "stop" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

yss

-0.73

aths

-0.73

 suscept

-0.72

ighth

-0.69

Versions

-0.69

 reconc

-0.67

Sov

-0.64

rity

-0.62

 abund

-0.62

xual

-0.62

POSITIVE LOGITS

gap

1.02

watch

1.01

lights

0.91

oppers

0.90

opping

0.78

watching

0.75

iem

0.73

down

0.72

kick

0.70

ions

0.68

Activations Density 0.028%

places or points where something, such as a schedule, journey, event, or process, comes to a halt or a designated end

occurrences of the word "stop" and its variations

No Comments

No Known Activations