INDEX

Explanations

phrases related to close proximity and confrontation

oai_token-act-pair · gpt-3.5-turbo

phrases related to cooperation or unity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

>[

-0.67

ARE

-0.65

essim

-0.64

Statement

-0.64

Streamer

-0.63

å¹

-0.63

ACP

-0.62

 Associ

-0.61

urable

-0.60

URA

-0.59

POSITIVE LOGITS

monds

0.71

 limb

0.70

 province

0.67

mond

0.64

 drawer

0.61

ether

0.61

cipline

0.60

 mouth

0.59

neck

0.59

 fists

0.58

Activations Density 0.103%

phrases related to close proximity and confrontation

phrases related to cooperation or unity

No Comments

No Known Activations