INDEX

Explanations

words related to intensity

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "sense" 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

orders

-0.67

swick

-0.65

atta

-0.65

Accessory

-0.65

OGR

-0.63

oths

-0.63

ODUCT

-0.63

amous

-0.63

amar

-0.61

available

-0.61

POSITIVE LOGITS

mble

2.00

ense

1.00

ly

0.92

entimes

0.83

iture

0.82

cre

0.80

ENSE

0.71

lihood

0.68

enses

0.65

 Ratio

0.64

Activations Density 0.013%

words related to intensity

occurrences of the word "sense" in various contexts

No Comments

No Known Activations