INDEX

Explanations

questions starting with the word "Why"

oai_token-act-pair · gpt-3.5-turbo

the word "Why" and related questioning phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

rop

-0.75

 Roller

-0.72

wrapper

-0.68

ymph

-0.67

bows

-0.67

interstitial

-0.65

amps

-0.64

oys

-0.63

ãĤ¹

-0.63

ryu

-0.62

POSITIVE LOGITS

soever

1.14

why

0.92

WHY

0.90

why

0.88

Why

0.88

Why

0.73

ihad

0.72

icago

0.71

 Does

0.70

iterranean

0.70

Activations Density 0.037%

questions starting with the word "Why"

the word "Why" and related questioning phrases

No Comments

No Known Activations