INDEX

Explanations

the letter "M" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

words related to medical or health issues

oai_token-act-pair · gpt-3.5-turbo

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

ãĤ¡

-0.69

 foul

-0.66

 Eleven

-0.66

 tips

-0.66

 yours

-0.65

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.65

 bubbles

-0.64

 center

-0.63

 Guinness

-0.63

é¾įå¥ĳå£«

-0.62

POSITIVE LOGITS

OST

1.16

ixed

1.13

iscal

1.13

uzzle

1.12

uppet

1.11

ONEY

1.11

useum

1.10

ambo

1.08

ugg

1.08

umbai

1.08

Activations Density 0.050%

the letter "M" in various contexts

words related to medical or health issues

No Comments

No Known Activations