INDEX

Explanations

phrases emphasizing a point or contrasting expectations

oai_token-act-pair · gpt-3.5-turbo

the phrase "not that" followed by a negative qualifier

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

å§«

-0.87

Dialogue

-0.80

izont

-0.74

Ń·

-0.73

rees

-0.71

afety

-0.69

rahim

-0.69

ãĥ¼ãĥ³

-0.68

Leaks

-0.68

ulus

-0.68

POSITIVE LOGITS

 simple

1.11

 easy

1.00

 uncommon

0.92

 kind

0.91

simple

0.90

way

0.88

 important

0.86

 fateful

0.84

 unusual

0.83

 complicated

0.83

Activations Density 0.059%

phrases emphasizing a point or contrasting expectations

the phrase "not that" followed by a negative qualifier

No Comments

No Known Activations