INDEX

Explanations

references to the media outlet "IGN"

oai_token-act-pair · gpt-3.5-turbo

references to the media outlet IGN

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

 Georgian

-0.77

zynski

-0.75

foot

-0.73

xual

-0.70

tons

-0.70

 Finnish

-0.69

kees

-0.69

annis

-0.69

 Eston

-0.67

 Azerbai

-0.66

POSITIVE LOGITS

VERTISEMENT

0.98

ORED

0.97

ITION

0.96

IGN

0.90

uable

0.85

ORE

0.84

ution

0.84

ITE

0.83

IFIED

0.82

ibly

0.81

Activations Density 0.014%

references to the media outlet "IGN"

references to the media outlet IGN

No Comments

No Known Activations