INDEX

Explanations

phrases related to being packed or crammed with items or people

oai_token-act-pair · gpt-3.5-turbo

terms related to being full or heavily loaded

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

Not in Any Lists

No Comments

Negative Logits

ateur

-0.84

shire

-0.80

tein

-0.77

 Parables

-0.75

failed

-0.68

framework

-0.66

 derive

-0.65

etheless

-0.65

rant

-0.65

chal

-0.65

POSITIVE LOGITS

 onto

1.00

packed

0.98

 shelves

0.95

 crates

0.92

llah

0.89

 bags

0.89

 into

0.87

pload

0.84

 packed

0.81

 groceries

0.79

Activations Density 0.076%

phrases related to being packed or crammed with items or people

terms related to being full or heavily loaded

No Comments

No Known Activations