INDEX

Explanations

phrases related to forceful actions or impacts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "through."

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

abet

-0.71

isted

-0.69

juven

-0.69

etus

-0.69

CTV

-0.66

OST

-0.65

onomy

-0.64

 whales

-0.64

arily

-0.64

IST

-0.64

POSITIVE LOGITS

)=(

0.70

drive

0.69

 waivers

0.67

inventoryQuantity

0.67

ierre

0.66

 Weld

0.64

 Rodrig

0.64

 Sussex

0.64

shaw

0.62

ensibly

0.61

Activations Density 0.046%

phrases related to forceful actions or impacts

instances of the word "through."

No Comments

No Known Activations