INDEX

Explanations

names or terms containing "Re"

oai_token-act-pair · gpt-3.5-turbo

the occurrences of the name "Re" 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

ãĥ¼ãĥĨãĤ£

-0.79

åŃ

-0.76

 Pebble

-0.73

DragonMagazine

-0.70

 à¨

-0.67

 Nieto

-0.67

 Nicarag

-0.65

 Korra

-0.65

£ı

-0.64

CPC

-0.64

POSITIVE LOGITS

levant

1.18

usable

1.14

asonable

1.09

actor

1.09

versible

1.07

becca

1.05

verend

1.05

ceive

1.04

clamation

1.04

acher

1.04

Activations Density 0.012%

names or terms containing "Re"

the occurrences of the name "Re" in various contexts

No Comments

No Known Activations