INDEX

Explanations

proper nouns related to a specific geographical location, Delaware

oai_token-act-pair · gpt-3.5-turbo

mentions of the state of Delaware

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

-0.75

icles

-0.74

ĸļ

-0.73

andr

-0.70

atic

-0.70

Ģ

-0.69

senal

-0.67

colo

-0.66

istic

-0.65

oras

-0.65

POSITIVE LOGITS

 Delaware

0.96

grass

0.76

wine

0.75

 County

0.73

 Downs

0.73

FINE

0.70

aware

0.68

 Shore

0.68

sylv

0.67

 Highlands

0.67

Activations Density 0.017%

proper nouns related to a specific geographical location, Delaware

mentions of the state of Delaware

No Comments

No Known Activations