INDEX

Explanations

phrases indicating the completion of a group or collection

oai_token-act-pair · gpt-3.5-turbo

the word "all" in various contexts, indicating inclusivity or completeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

•All the Features!

No Comments

Negative Logits

gee

-0.65

 Rouge

-0.61

hips

-0.61

leep

-0.60

rouse

-0.59

zik

-0.57

sov

-0.56

robe

-0.56

gap

-0.55

aminer

-0.55

POSITIVE LOGITS

 kinds

1.45

 sorts

1.44

igators

1.16

usions

1.12

ocating

1.12

igator

1.11

 manner

1.00

ocations

1.00

ogene

0.99

 facets

0.95

Activations Density 0.109%

phrases indicating the completion of a group or collection

the word "all" in various contexts, indicating inclusivity or completeness

No Comments

No Known Activations