INDEX

Explanations

locations or places related to the city of Dhaka

oai_token-act-pair · gpt-3.5-turbo

references to the city of Dhaka and its variations in name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

éĹĺ

-1.01

*/(

-0.94

 wheelchair

-0.72

 Crimean

-0.71

swick

-0.70

izations

-0.70

 therapy

-0.69

eering

-0.68

 referrals

-0.67

secut

-0.66

POSITIVE LOGITS

Dh

1.15

onest

1.07

awan

1.05

abal

1.03

arm

0.98

ancing

0.97

aval

0.96

assi

0.92

uran

0.92

izoph

0.90

Activations Density 0.003%

locations or places related to the city of Dhaka

references to the city of Dhaka and its variations in name

No Comments

No Known Activations