INDEX

Explanations

phrases related to impossibility or extreme difficulty

oai_token-act-pair · gpt-3.5-turbo

phrases expressing the concept of impossibility

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

oola

-0.85

avia

-0.84

aina

-0.81

ivities

-0.77

mens

-0.76

soType

-0.74

notations

-0.74

lance

-0.73

anmar

-0.73

ijuana

-0.73

POSITIVE LOGITS

 feas

0.78

ossible

0.74

 conceivable

0.72

 foreseeable

0.71

 unanim

0.70

 imaginable

0.69

ãĥĢ

0.69

 unless

0.68

 impossible

0.67

 obstruction

0.67

Activations Density 0.034%

phrases related to impossibility or extreme difficulty

phrases expressing the concept of impossibility

No Comments

No Known Activations