INDEX

Explanations

proper nouns related to people or brands

oai_token-act-pair · gpt-3.5-turbo

mentions of individuals and brands related to beer and brewing

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

hips

-0.84

pher

-0.78

tics

-0.78

craft

-0.75

itatively

-0.75

bol

-0.74

yrinth

-0.73

ount

-0.71

peria

-0.70

onet

-0.69

POSITIVE LOGITS

 Hein

1.00

 sandwiches

0.90

Whe

0.79

lein

0.76

 sandwich

0.76

 Beans

0.75

 Foods

0.75

 mustard

0.74

 hamb

0.71

 bisc

0.71

Activations Density 0.024%

proper nouns related to people or brands

mentions of individuals and brands related to beer and brewing

No Comments

No Known Activations