INDEX

Explanations

words related to medical conditions, protein expressions, and scientific terms

oai_token-act-pair · gpt-3.5-turbo

terms related to medical or biological conditions and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

CLASSIFIED

-0.89

DragonMagazine

-0.87

éĹĺ

-0.86

HAEL

-0.83

 Tradable

-0.81

 Rebels

-0.81

å§«

-0.79

âĶģ

-0.78

 guiActiveUnfocused

-0.77

ORED

-0.77

POSITIVE LOGITS

ox

1.21

oxic

1.10

phthal

1.08

amin

1.05

âĢĲ

1.01

cyt

0.99

ogenic

0.98

otropic

0.97

ogen

0.95

oxy

0.95

Activations Density 0.203%

words related to medical conditions, protein expressions, and scientific terms

terms related to medical or biological conditions and their effects

No Comments

No Known Activations