INDEX

Explanations

words related to identification and travel documents, specifically focusing on the term "Pass."

oai_token-act-pair · gpt-3.5-turbo

references to the Passover holiday

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

ãĤ¼ãĤ¦ãĤ¹

-1.03

ä¸ī

-0.83

 GOODMAN

-0.71

ASP

-0.62

 rook

-0.62

 Cortex

-0.61

PLA

-0.60

Pwr

-0.60

 Admir

-0.59

Kut

-0.58

POSITIVE LOGITS

engers

1.44

wd

1.30

enger

1.27

words

1.13

es

1.10

ioned

1.05

aic

1.05

ports

1.04

port

0.95

phrase

0.93

Activations Density 0.016%

words related to identification and travel documents, specifically focusing on the term "Pass."

references to the Passover holiday

No Comments

No Known Activations