INDEX

Explanations

superlatives and achievements

oai_token-act-pair · gpt-3.5-turbo

possessive constructions indicating worldwide significance

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xual

-0.87

ality

-0.80

nels

-0.80

rade

-0.79

ĳå£«

-0.77

ËĪ

-0.76

yang

-0.74

lp

-0.74

ï¸ı

-0.72

nell

-0.71

POSITIVE LOGITS

 largest

1.14

 richest

1.05

 fastest

1.04

 finest

1.00

 tallest

1.00

 biggest

0.98

 longest

0.96

 greatest

0.96

 wealthiest

0.96

 poorest

0.96

Activations Density 0.065%

superlatives and achievements

possessive constructions indicating worldwide significance

No Comments

No Known Activations