INDEX

Explanations

proper nouns and names, particularly focusing on the name "Hers"

oai_token-act-pair · gpt-3.5-turbo

references to the brand "Hers" and related names

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

 Martial

-0.72

 Samoa

-0.69

 Mecca

-0.67

 Lomb

-0.67

 Antar

-0.67

 Kenyan

-0.67

 martial

-0.66

 partic

-0.65

âĶĢâĶĢ

-0.64

 nomine

-0.63

POSITIVE LOGITS

hey

1.11

chel

1.10

 Hers

1.03

bet

1.02

burgh

0.97

hel

0.96

chell

0.95

bour

0.94

bling

0.94

cot

0.91

Activations Density 0.014%

proper nouns and names, particularly focusing on the name "Hers"

references to the brand "Hers" and related names

No Comments

No Known Activations