INDEX

Explanations

proper nouns denoting superlatives, such as "largest."

oai_token-act-pair · gpt-3.5-turbo

instances of the word "largest" related to various subjects

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

jad

-0.84

bara

-0.74

earth

-0.72

yang

-0.72

fy

-0.71

Mub

-0.71

styles

-0.71

bel

-0.70

work

-0.70

onso

-0.70

POSITIVE LOGITS

gest

0.93

 intestine

0.89

(>

0.85

 scale

0.81

 creditor

0.81

 swath

0.79

 shareholder

0.77

 extant

0.77

 denomination

0.75

 chunk

0.75

Activations Density 0.025%

proper nouns denoting superlatives, such as "largest."

instances of the word "largest" related to various subjects

No Comments

No Known Activations