INDEX

Explanations

words related to evaluation and judgment, indicating strong assessments and opinions

oai_token-act-pair · gpt-3.5-turbo

repetitive use of the verb "is" across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

racuse

-0.70

want

-0.70

ãĤ¼ãĤ¦ãĤ¹

-0.67

ossom

-0.67

inav

-0.64

ESE

-0.64

halla

-0.64

onnaissance

-0.64

 Calls

-0.64

ukong

-0.64

POSITIVE LOGITS

 unlikely

1.31

 technically

1.24

 certainly

1.23

nt

1.22

not

1.22

 undeniably

1.20

 still

1.16

 admittedly

1.14

 definitely

1.12

NOT

1.12

Activations Density 0.483%

words related to evaluation and judgment, indicating strong assessments and opinions

repetitive use of the verb "is" across various contexts

No Comments

No Known Activations