INDEX

Explanations

proper nouns referring to individuals, likely names

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals, particularly "Gret" and related names

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

shirt

-0.80

xual

-0.78

termin

-0.72

shirts

-0.70

panel

-0.69

 checkout

-0.67

zees

-0.64

REDACTED

-0.62

 Pigs

-0.62

 Jinping

-0.61

POSITIVE LOGITS

alus

0.93

sburg

0.89

olf

0.84

heim

0.80

inka

0.79

Ã¼r

0.79

ald

0.78

ersen

0.75

alf

0.75

ĳ

0.74

Activations Density 0.030%

proper nouns referring to individuals, likely names

references to specific individuals, particularly "Gret" and related names

No Comments

No Known Activations