INDEX

Explanations

phrases related to expressing opinions or preferences

oai_token-act-pair · gpt-3.5-turbo

expressions of opinion or preference

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

 arrivals

-0.70

ouf

-0.68

ourse

-0.63

urate

-0.62

oward

-0.57

izons

-0.57

gery

-0.57

uart

-0.56

 dual

-0.56

cend

-0.56

POSITIVE LOGITS

ById

0.76

 yeah

0.76

66666666

0.74

Ö¼

0.70

 damned

0.67

esm

0.67

 Unloaded

0.66

 albeit

0.65

 Bits

0.63

 anyway

0.63

Activations Density 0.351%

phrases related to expressing opinions or preferences

expressions of opinion or preference

No Comments

No Known Activations