INDEX

Explanations

polarizing statements or opinions

oai_token-act-pair · gpt-3.5-turbo

instances of punctuation, particularly commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

FTWARE

-0.67

olutions

-0.62

 Fired

-0.59

LOAD

-0.59

 Balanced

-0.59

ORPG

-0.59

ãĤ´ãĥ³

-0.58

youtu

-0.58

Reward

-0.57

/?

-0.55

POSITIVE LOGITS

 alas

1.17

 unsurprisingly

1.17

uh

1.06

 understandably

0.99

 unfortunately

0.99

 frankly

0.99

 indeed

0.98

um

0.97

 admittedly

0.95

 moreover

0.93

Activations Density 0.089%

polarizing statements or opinions

instances of punctuation, particularly commas

No Comments

No Known Activations