INDEX

Explanations

words related to quantities and statistics

oai_token-act-pair · gpt-3.5-turbo

nouns or terms indicating statistics, entities, or measurements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 initialization

-0.65

 advocacy

-0.64

 modernization

-0.63

 affirmation

-0.62

 implication

-0.60

 abstraction

-0.59

 Sabres

-0.59

 parity

-0.58

 skelet

-0.58

 Commissioners

-0.58

POSITIVE LOGITS

 thereof

0.73

.[

0.72

é¾įåĸļå£«

0.71

 alike

0.71

0.70

hip

0.69

SPONSORED

0.69

paces

0.68

natureconservancy

0.68

hots

0.67

Activations Density 0.704%

words related to quantities and statistics

nouns or terms indicating statistics, entities, or measurements

No Comments

No Known Activations