INDEX

Explanations

phrases related to personal opinions or viewpoints

oai_token-act-pair · gpt-3.5-turbo

phrases related to decision-making and emotional reactions

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

 respectively

-0.68

estones

-0.67

icipated

-0.61

arthed

-0.58

 Browse

-0.58

ominated

-0.57

begin

-0.57

aired

-0.57

OHN

-0.56

imentary

-0.56

POSITIVE LOGITS

 ..."

1.04

 âĢ¦"

0.98

 idiots

0.94

 scapego

0.94

 stupidity

0.91

 disrespect

0.89

?"

0.86

 stupid

0.86

 slander

0.84

Activations Density 0.903%

phrases related to personal opinions or viewpoints

phrases related to decision-making and emotional reactions

No Comments

No Known Activations