INDEX

Explanations

phrases related to a specific point in time

oai_token-act-pair · gpt-3.5-turbo

references to specific points in time

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

dimension

-0.63

MON

-0.61

anium

-0.60

ãĥ¼ãĥ

-0.59

icut

-0.59

amaz

-0.59

 neighb

-0.58

ãĥ¼ãĥĨãĤ£

-0.57

aila

-0.57

atts

-0.56

POSITIVE LOGITS

 onwards

0.93

abouts

0.87

 onward

0.85

endment

0.75

upon

0.69

cture

0.67

 moot

0.67

points

0.67

ebin

0.62

gue

0.61

Activations Density 0.039%

phrases related to a specific point in time

references to specific points in time

No Comments

No Known Activations