INDEX

Explanations

proper nouns or technical terms, potentially in a specific language

oai_token-act-pair · gpt-3.5-turbo

instances of the character 'Ļ' in various contexts

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

iosyncr

-0.96

ricanes

-0.92

raviolet

-0.91

ickets

-0.76

ribly

-0.75

ategory

-0.74

onal

-0.73

urity

-0.72

icket

-0.72

anwhile

-0.72

POSITIVE LOGITS

wagen

0.80

ston

0.71

ister

0.71

 Grimoire

0.70

ļé

0.70

AUT

0.69

ery

0.68

STON

0.67

istry

0.66

ãģ®éŃĶ

0.66

Activations Density 0.034%

proper nouns or technical terms, potentially in a specific language

instances of the character 'Ļ' in various contexts

No Comments

No Known Activations