INDEX

Explanations

phrases related to tags or labeling

oai_token-act-pair · gpt-3.5-turbo

occurrences of specific keywords or tags related to topics of discussion

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

isky

-0.78

 Seym

-0.71

 Monetary

-0.67

¬¼

-0.65

theless

-0.64

 Side

-0.62

gow

-0.60

 sclerosis

-0.59

rawdownloadcloneembedreportprint

-0.58

 Continental

-0.58

POSITIVE LOGITS

gers

1.19

ged

1.15

alog

1.12

gery

1.07

ger

1.02

ging

1.01

tag

0.95

tags

0.94

liam

0.94

lines

0.93

Activations Density 0.038%

phrases related to tags or labeling

occurrences of specific keywords or tags related to topics of discussion

No Comments

No Known Activations