INDEX

Explanations

entities related to names and organizations

oai_token-act-pair · gpt-3.5-turbo

specific acronyms or names relevant to industries or organizations

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

 Dise

-0.73

adr

-0.65

Bench

-0.64

 conclud

-0.63

multipl

-0.62

LIM

-0.62

 Mehran

-0.62

MRI

-0.60

HAEL

-0.60

tumblr

-0.60

POSITIVE LOGITS

ilver

0.86

phrine

0.81

idia

0.75

onsense

0.75

abies

0.74

ovych

0.70

oxide

0.69

ensical

0.68

gaard

0.68

acht

0.66

Activations Density 0.491%

entities related to names and organizations

specific acronyms or names relevant to industries or organizations

No Comments

No Known Activations