INDEX

Explanations

proper nouns or locations, specifically focusing on names of countries

oai_token-act-pair · gpt-3.5-turbo

mentions of geographic locations or proper nouns related to places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

deck

-0.71

bread

-0.69

worn

-0.67

kid

-0.66

low

-0.65

spot

-0.65

iT

-0.64

 Attribution

-0.64

geist

-0.62

 roofs

-0.62

POSITIVE LOGITS

Ã°

1.01

cci

0.96

Ã±

0.95

ÄŁ

0.86

ccess

0.83

zzi

0.82

qt

0.80

pload

0.79

Ã±o

0.79

 Kenobi

0.78

Activations Density 0.041%

proper nouns or locations, specifically focusing on names of countries

mentions of geographic locations or proper nouns related to places

No Comments

No Known Activations