INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

words and terms related to power, governance, and authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

roman

-0.68

erb

-0.67

CP

-0.67

COM

-0.66

MP

-0.64

rices

-0.64

AW

-0.63

eb

-0.63

Mob

-0.63

CSS

-0.62

POSITIVE LOGITS

theless

0.78

abwe

0.69

Ó

0.68

udence

0.64

henko

0.64

ruction

0.63

ensional

0.62

ãĤ£

0.62

zyk

0.62

sson

0.61

Activations Density 0.159%

proper nouns

words and terms related to power, governance, and authority

No Comments

No Known Activations