INDEX

Explanations

phrases related to negative emotions and events

oai_token-act-pair · gpt-3.5-turbo

negative connotations associated with disgust and disappointment

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 livest

-0.65

stadt

-0.64

yip

-0.63

arella

-0.62

 hypers

-0.61

Ô

-0.61

 confir

-0.60

belt

-0.57

 congr

-0.56

rays

-0.56

POSITIVE LOGITS

ption

1.05

owship

0.94

ptive

0.90

akable

0.87

ointed

0.84

untled

0.80

agement

0.79

ction

0.79

ensing

0.78

achment

0.77

Activations Density 0.037%

phrases related to negative emotions and events

negative connotations associated with disgust and disappointment

No Comments

No Known Activations