INDEX

Explanations

proper names of individuals or entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of people and places

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

 ..."

-0.77

Americ

-0.72

-0.67

Wes

-0.67

Scar

-0.66

ãĤ¡

-0.62

Wyr

-0.61

-0.60

 Chero

-0.59

åĤ

-0.58

POSITIVE LOGITS

 meanwhile

1.04

 responded

1.03

 denies

0.98

 countered

0.93

 apologized

0.93

 reportedly

0.93

 vetoed

0.90

 reacted

0.88

 thanked

0.87

 replied

0.86

Activations Density 0.392%

proper names of individuals or entities

proper nouns, particularly names of people and places

No Comments

No Known Activations