INDEX

Explanations

phrases expressing superiority or comparison in a positive light

oai_token-act-pair · gpt-3.5-turbo

expressions emphasizing superiority or preference

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

ß

-0.70

ô

-0.69

yip

-0.69

lish

-0.68

Þ

-0.66

ï¿½ï¿½ï¿½ï¿½

-0.63

colour

-0.63

DP

-0.62

ÃĥÃĤ

-0.62

dh

-0.61

POSITIVE LOGITS

 Trace

0.66

 escaping

0.64

 anybody

0.63

Way

0.63

 temptation

0.62

 whatsoever

0.61

THING

0.61

osal

0.60

 scrolling

0.60

 anyone

0.59

Activations Density 0.201%

phrases expressing superiority or comparison in a positive light

expressions emphasizing superiority or preference

No Comments

No Known Activations