INDEX

Explanations

situations or tasks related to online activities like gaming and memberships

oai_token-act-pair · gpt-3.5-turbo

terms related to performance metrics or achievement recognition

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

oscope

-0.79

 Zucker

-0.73

 fabricated

-0.68

 crib

-0.67

osc

-0.66

Ake

-0.64

rub

-0.63

ouf

-0.63

 plagiar

-0.63

aired

-0.61

POSITIVE LOGITS

Merit

1.38

ertodd

1.11

Activity

1.08

iculty

0.96

 Donation

0.91

 Thumbnails

0.80

Offline

0.80

amins

0.78

Bitcoin

0.77

 Payments

0.77

Activations Density 0.022%

situations or tasks related to online activities like gaming and memberships

terms related to performance metrics or achievement recognition

No Comments

No Known Activations