INDEX

Explanations

nouns and adjectives

oai_token-act-pair · gpt-3.5-turbo

specific types of grammatical elements, particularly nouns and adjectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

loo

-0.80

porting

-0.72

 Klux

-0.71

KER

-0.70

inness

-0.70

inventoryQuantity

-0.64

ilated

-0.63

-0.62

 Palest

-0.62

quished

-0.62

POSITIVE LOGITS

 adjective

0.74

 trope

0.74

pmwiki

0.71

 adject

0.67

odic

0.67

 tropes

0.66

onsense

0.65

witz

0.65

ãģĻ

0.65

ures

0.65

Activations Density 0.016%

nouns and adjectives

specific types of grammatical elements, particularly nouns and adjectives

No Comments

No Known Activations