INDEX

Explanations

words related to medication or treatment

oai_token-act-pair · gpt-3.5-turbo

the presence of the token "ke" in various forms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ourced

-0.69

 Palestin

-0.68

ourcing

-0.67

ohydrate

-0.64

é¾

-0.62

ashtra

-0.62

aceutical

-0.61

anamo

-0.60

MpServer

-0.60

aciously

-0.59

POSITIVE LOGITS

ller

1.34

llers

1.33

ptic

1.17

vich

1.09

lling

1.07

ls

1.03

letal

1.01

jriwal

0.95

rette

0.94

rer

0.93

Activations Density 0.027%

words related to medication or treatment

the presence of the token "ke" in various forms

No Comments

No Known Activations