INDEX

Explanations

words related to names or titles, specifically those ending in 'ay'

oai_token-act-pair · gpt-3.5-turbo

the word "Ay" and its variations in different contexts

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

ipeg

-0.83

hester

-0.69

urally

-0.68

ãĤ´ãĥ³

-0.65

å¥³

-0.64

 Archdemon

-0.64

ITIES

-0.63

ugal

-0.63

wcs

-0.63

wom

-0.63

POSITIVE LOGITS

alam

0.89

cott

0.86

nor

0.84

walk

0.84

uki

0.83

atana

0.83

onet

0.82

alde

0.82

nard

0.79

yy

0.79

Activations Density 0.040%

words related to names or titles, specifically those ending in 'ay'

the word "Ay" and its variations in different contexts

No Comments

No Known Activations