INDEX

Explanations

evaluative phrases or words related to performance

oai_token-act-pair · gpt-3.5-turbo

phrases related to ratings or evaluations of quality

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

atars

-0.64

 Cosponsors

-0.63

pora

-0.63

apters

-0.61

untled

-0.61

uay

-0.59

ilater

-0.59

arette

-0.58

irez

-0.58

anchez

-0.58

POSITIVE LOGITS

Sle

0.60

natureconservancy

0.59

 chops

0.58

expensive

0.58

 congr

0.56

Surv

0.55

 outweigh

0.55

âĺħâĺħ

0.54

 Efficiency

0.53

 Mahjong

0.53

Activations Density 1.305%

evaluative phrases or words related to performance

phrases related to ratings or evaluations of quality

No Comments

No Known Activations