INDEX

Explanations

specific days of the week

oai_token-act-pair · gpt-3.5-turbo

specific days of the week and references to time

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rosse

-0.86

 Mehran

-0.68

ographed

-0.66

 Franch

-0.66

WER

-0.65

"],"

-0.65

kef

-0.63

 Canaver

-0.63

edly

-0.62

 Â¶

-0.62

POSITIVE LOGITS

 silence

0.67

days

0.66

 deadline

0.65

dig

0.64

pack

0.63

 afternoon

0.63

aria

0.63

 election

0.63

's

0.62

 skies

0.61

Activations Density 0.121%

specific days of the week

specific days of the week and references to time

No Comments

No Known Activations