INDEX

Explanations

names starting with "Nor"

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific name or entity, primarily "Nor."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

place

-0.70

AGES

-0.70

Premium

-0.69

Ĥİ

-0.65

ULT

-0.65

liquid

-0.62

ULAR

-0.62

ulate

-0.61

uated

-0.61

MODE

-0.61

POSITIVE LOGITS

wegian

0.98

phan

0.96

berto

0.96

pheus

0.92

nir

0.92

rien

0.90

withstanding

0.84

thodox

0.79

icia

0.78

onso

0.78

Activations Density 0.006%

names starting with "Nor"

mentions of a specific name or entity, primarily "Nor."

No Comments

No Known Activations