INDEX

Explanations

words related to importance or emphasis

oai_token-act-pair · gpt-3.5-turbo

terms related to major roles or functions

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

erved

-0.92

ceans

-0.80

erves

-0.79

ork

-0.78

paio

-0.77

LV

-0.75

ossession

-0.72

apons

-0.70

aping

-0.69

utics

-0.68

POSITIVE LOGITS

 reason

1.12

 culprit

1.09

stay

1.03

 source

1.00

 contributor

0.96

 proponent

0.94

 distinguishing

0.93

 reasons

0.90

 obstacle

0.90

 difference

0.86

Activations Density 0.092%

words related to importance or emphasis

terms related to major roles or functions

No Comments

No Known Activations