INDEX

Explanations

words related to political discussions, debates, and announcements

oai_token-act-pair · gpt-3.5-turbo

markers and symbols that indicate sections or transitions in written content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 joints

-0.62

oggles

-0.59

 creat

-0.59

 illust

-0.59

 rave

-0.59

 inspiration

-0.58

intend

-0.58

 legends

-0.58

 commissions

-0.58

 sake

-0.58

POSITIVE LOGITS

Reuters

0.83

Analysis

0.83

Read

0.82

 WATCHED

0.80

 Continued

0.79

Meanwhile

0.78

zbollah

0.77

RELATED

0.77

ADVERTISEMENT

0.75

np

0.75

Activations Density 0.121%

words related to political discussions, debates, and announcements

markers and symbols that indicate sections or transitions in written content

No Comments

No Known Activations