INDEX

Explanations

names of individuals which could be from different contexts or scenarios

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people

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

į

-0.65

LEASE

-0.63

 Bent

-0.61

 Pixie

-0.61

RJ

-0.60

Â¯

-0.60

ÑĮ

-0.59

Tup

-0.59

 Alto

-0.58

Lex

-0.58

POSITIVE LOGITS

enegger

1.21

 testified

0.98

 himself

0.84

 herself

0.80

 told

0.78

 remembers

0.77

 wrote

0.77

 oversaw

0.76

 underwent

0.76

 admitted

0.75

Activations Density 0.131%

names of individuals which could be from different contexts or scenarios

proper nouns, specifically names of people

No Comments

No Known Activations