INDEX

Explanations

negative statements using the phrase "don't."

oai_token-act-pair · gpt-3.5-turbo

negations, particularly involving the phrase "don't."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ãĤ¤ãĥĪ

-0.85

ãĥĥãĥī

-0.81

ãĥ³ãĤ¸

-0.81

ãĥĵ

-0.80

ORGE

-0.79

ãĤ¶

-0.74

ãĥª

-0.72

ãĥ¼ãĥĨ

-0.71

ãĥ¼ãĥĨãĤ£

-0.70

ñ

-0.70

POSITIVE LOGITS

 already

0.99

hin

0.90

 comply

0.85

 succeed

0.84

 cooperate

0.79

 resolve

0.77

 agree

0.73

 careful

0.71

 complying

0.70

 satisf

0.70

Activations Density 0.137%

negative statements using the phrase "don't."

negations, particularly involving the phrase "don't."

No Comments

No Known Activations