INDEX

Explanations

adjectives or verbs related to criticism or complacency

oai_token-act-pair · gpt-3.5-turbo

terms related to complaints or grievances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

hyde

-0.90

bucks

-0.76

eele

-0.75

EStream

-0.74

terday

-0.74

¥µ

-0.68

HAEL

-0.67

xon

-0.66

plane

-0.65

Downloadha

-0.65

POSITIVE LOGITS

acent

1.22

ainer

1.01

icating

1.01

antly

0.94

icates

0.93

iable

0.85

iability

0.83

ause

0.83

icit

0.82

isance

0.82

Activations Density 0.006%

adjectives or verbs related to criticism or complacency

terms related to complaints or grievances

No Comments

No Known Activations