INDEX

Explanations

words related to geographical locations or names

oai_token-act-pair · gpt-3.5-turbo

names of locations or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cosponsors

-0.82

hement

-0.70

taboola

-0.69

bably

-0.68

 feder

-0.67

natureconservancy

-0.66

uania

-0.65

Äĩ

-0.65

ItemTracker

-0.64

 withstand

-0.64

POSITIVE LOGITS

asca

0.72

apor

0.67

opol

0.62

 condol

0.60

abe

0.58

ollah

0.58

 womb

0.58

nis

0.58

quin

0.58

hoe

0.58

Activations Density 0.210%

words related to geographical locations or names

names of locations or places

No Comments

No Known Activations