INDEX

Explanations

keywords related to significant events, breakthroughs, or important appearances

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "appearance" and similar forms, indicating a focus on visibility or presence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

omical

-0.76

fax

-0.67

hiba

-0.63

 waive

-0.62

ledge

-0.61

 certify

-0.59

imir

-0.59

ave

-0.58

 disclose

-0.58

rib

-0.58

POSITIVE LOGITS

ablished

0.75

ãĤ¶

0.71

aeda

0.70

ORN

0.70

unin

0.69

ãĤ¼ãĤ¦ãĤ¹

0.68

occupied

0.68

 Frieza

0.66

groups

0.65

Occup

0.65

Activations Density 0.411%

keywords related to significant events, breakthroughs, or important appearances

occurrences of the word "appearance" and similar forms, indicating a focus on visibility or presence

No Comments

No Known Activations