INDEX

Explanations

proper nouns or names, specifically focused on the name "Troy"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Troy."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

INESS

-0.81

awar

-0.75

pmwiki

-0.73

iquid

-0.72

ãĥĥãĤ¯

-0.70

ubric

-0.69

ivia

-0.68

 pity

-0.68

merga

-0.67

ivities

-0.67

POSITIVE LOGITS

alty

0.91

alties

0.90

ĳå£«

0.81

neau

0.79

al

0.77

imet

0.75

don

0.75

tics

0.74

er

0.73

nce

0.72

Activations Density 0.032%

proper nouns or names, specifically focused on the name "Troy"

mentions of the word "Troy."

No Comments

No Known Activations