INDEX

Explanations

phrases or words that draw attention to specific information or issues

oai_token-act-pair · gpt-3.5-turbo

the word "highlight" and its variations indicating emphasis or focus on particular subjects

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

itte

-0.71

shake

-0.71

ja

-0.69

hell

-0.69

mia

-0.68

thood

-0.67

soever

-0.64

cill

-0.63

onew

-0.63

onz

-0.62

POSITIVE LOGITS

 weaknesses

0.93

 shortcomings

0.83

 similarities

0.81

 contradictions

0.80

 flaws

0.79

 inconsistencies

0.78

 highlights

0.77

 differences

0.76

 milestones

0.75

 vulnerabilities

0.75

Activations Density 0.063%

phrases or words that draw attention to specific information or issues

the word "highlight" and its variations indicating emphasis or focus on particular subjects

No Comments

No Known Activations