INDEX

Explanations

proper nouns preceded by the word "the"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

intage

-0.75

ãĥĩãĤ£

-0.73

allery

-0.71

 Constantin

-0.69

ca

-0.68

foundland

-0.68

ACY

-0.67

ĳå£«

-0.67

rano

-0.66

âĺ

-0.63

POSITIVE LOGITS

 structured

0.77

 unfolded

0.77

 stacked

0.74

 pans

0.72

 fared

0.72

 stacks

0.71

ribed

0.71

 differs

0.68

 disparate

0.67

 fragmented

0.66

Activations Density 0.169%

proper nouns preceded by the word "the"

instances of the word "the" in various contexts

No Comments

No Known Activations