INDEX

Explanations

instances of the word "used"

oai_token-act-pair · gpt-3.5-turbo

the word "used" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Hai

-0.69

bitious

-0.69

-0.67

awk

-0.67

gee

-0.67

bow

-0.66

brother

-0.65

peat

-0.65

volent

-0.64

Ń·

-0.62

POSITIVE LOGITS

 condoms

0.82

FUL

0.78

fulness

0.78

fully

0.77

 extensively

0.73

 Used

0.70

 sparing

0.70

 phrases

0.68

 borrowed

0.68

 contacts

0.66

Activations Density 0.043%

instances of the word "used"

the word "used" in various contexts

No Comments

No Known Activations