INDEX

Explanations

adjectives indicating negative characteristics or behaviors

oai_token-act-pair · gpt-3.5-turbo

adjectives that suggest negative qualities or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ften

-0.78

 Originally

-0.73

 THERE

-0.70

ilogy

-0.67

undrum

-0.66

 smelled

-0.65

ocene

-0.63

ittee

-0.62

ansion

-0.62

claimer

-0.62

POSITIVE LOGITS

 proportions

0.93

 amounts

0.91

 situations

0.88

 occasions

0.87

 quantities

0.84

 levels

0.81

 interpretations

0.79

 circumstances

0.78

 periods

0.77

 ones

0.77

Activations Density 0.530%

adjectives indicating negative characteristics or behaviors

adjectives that suggest negative qualities or conditions

No Comments

No Known Activations