INDEX

Explanations

words related to negative emotions or attitudes towards a person or situation

oai_token-act-pair · gpt-3.5-turbo

negative sentiments and expressions of disappointment or disgust

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

glers

-0.72

 cycle

-0.71

 Transition

-0.69

 hike

-0.69

 sealing

-0.68

 hiking

-0.68

 rotation

-0.68

 density

-0.67

 playback

-0.66

 flow

-0.65

POSITIVE LOGITS

ceptive

1.26

ignant

1.24

atisf

1.19

interested

1.16

otent

1.15

respect

1.12

urious

1.12

isive

1.10

assion

1.08

righteous

1.07

Activations Density 0.132%

words related to negative emotions or attitudes towards a person or situation

negative sentiments and expressions of disappointment or disgust

No Comments

No Known Activations