INDEX

Explanations

words related to proper nouns, particularly names and locations

oai_token-act-pair · gpt-3.5-turbo

specific letters or characters appearing repeatedly in a text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 conscience

-0.70

llah

-0.68

OPLE

-0.66

merce

-0.65

FTA

-0.64

Pwr

-0.62

 PROC

-0.59

 ACTIONS

-0.59

ãģ®éŃĶ

-0.59

 tumble

-0.58

POSITIVE LOGITS

heed

1.01

uania

0.91

ttle

0.91

cious

0.85

emort

0.84

ounge

0.84

vel

0.84

achev

0.81

warm

0.79

ansk

0.79

Activations Density 0.086%

words related to proper nouns, particularly names and locations

specific letters or characters appearing repeatedly in a text

No Comments

No Known Activations