INDEX

Explanations

phrases related to measurements and quantification

oai_token-act-pair · gpt-3.5-turbo

terms related to measurement systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

lez

-0.79

osate

-0.72

 Safari

-0.71

 Reserve

-0.68

olla

-0.67

sle

-0.67

ozy

-0.67

illard

-0.65

burning

-0.65

herty

-0.65

POSITIVE LOGITS

enance

0.81

Quantity

0.78

downs

0.78

icle

0.77

eters

0.77

MENTS

0.76

 measuring

0.76

urgy

0.76

asured

0.75

icles

0.75

Activations Density 0.046%

phrases related to measurements and quantification

terms related to measurement systems

No Comments

No Known Activations