INDEX

Explanations

words related to medical conditions such as "karmic"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "k"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

•words starting with k

No Comments

Negative Logits

Ø©

-0.82

IBLE

-0.79

éĹĺ

-0.74

terday

-0.70

 Malf

-0.70

ãĥ¼ãĥĨãĤ£

-0.70

 expires

-0.67

ÙĴ

-0.66

 Rica

-0.66

 Staples

-0.66

POSITIVE LOGITS

idd

1.27

itty

1.22

ippers

1.13

appa

1.12

etchup

1.08

ipp

1.07

ratom

1.03

irk

1.01

rieg

1.00

erry

0.99

Activations Density 0.022%

words related to medical conditions such as "karmic"

occurrences of the letter "k"

No Comments

No Known Activations