INDEX

Explanations

phrases related to evaluation, judgment, and assessment

oai_token-act-pair · gpt-3.5-turbo

terms related to regulation and positioning

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

moon

-0.65

Ranked

-0.64

manent

-0.62

İĭ

-0.61

hang

-0.60

iggins

-0.60

idge

-0.59

cessive

-0.58

ĪĴ

-0.58

kay

-0.57

POSITIVE LOGITS

 geographically

0.77

entious

0.72

abouts

0.70

 aback

0.67

 antioxid

0.67

by

0.62

icative

0.62

uble

0.60

ombat

0.59

uries

0.59

Activations Density 0.181%

phrases related to evaluation, judgment, and assessment

terms related to regulation and positioning

No Comments

No Known Activations