INDEX

Explanations

phrases indicating information or claims made by others

oai_token-act-pair · gpt-3.5-turbo

instances of the word "said," indicating reported speech or claims

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

AMA

-0.67

 Submission

-0.62

å¼

-0.62

cession

-0.61

enegger

-0.60

legal

-0.59

ettlement

-0.58

Interstitial

-0.58

ierra

-0.57

 wedge

-0.56

POSITIVE LOGITS

dylib

0.81

 anecd

0.80

 goodbye

0.79

 sarcast

0.72

hap

0.65

 favorites

0.65

 farewell

0.64

onna

0.61

ril

0.60

to

0.58

Activations Density 0.072%

phrases indicating information or claims made by others

instances of the word "said," indicating reported speech or claims

No Comments

No Known Activations