INDEX

Explanations

phrases related to locations, specifically places starting with the letter "W"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'W' in various contexts

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

 succeeding

-0.75

arial

-0.73

 gratification

-0.68

 afore

-0.67

 headache

-0.66

 Prelude

-0.66

 duplication

-0.64

uate

-0.64

 enclosed

-0.63

 predators

-0.63

POSITIVE LOGITS

ITNESS

1.23

ITCH

1.19

edge

1.17

INGS

1.16

OW

1.15

atts

1.15

atson

1.15

OOD

1.15

ipe

1.12

aver

1.12

Activations Density 0.034%

phrases related to locations, specifically places starting with the letter "W"

occurrences of the letter 'W' in various contexts

No Comments

No Known Activations