INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

locations or contexts associated with the word "near."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

alian

-0.77

ilus

-0.76

dayName

-0.76

UX

-0.76

Percent

-0.72

BILL

-0.70

azeera

-0.70

etti

-0.68

ÑĮ

-0.67

oleon

-0.67

POSITIVE LOGITS

shore

0.98

sighted

0.88

 Bethlehem

0.84

 misses

0.81

 Yosemite

0.77

 Fresno

0.74

 Wembley

0.73

 Vancouver

0.73

ctic

0.73

 Mount

0.72

Activations Density 0.027%

locations or places

locations or contexts associated with the word "near."

No Comments

No Known Activations