INDEX

Explanations

molecular or medical terms related to biological processes

oai_token-act-pair · gpt-3.5-turbo

terms associated with physiological processes and medical conditions

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

Not in Any Lists

No Comments

Negative Logits

 Grounds

-0.78

 Benny

-0.77

 Fool

-0.75

 Monthly

-0.75

 Purg

-0.74

 Yard

-0.72

 Manor

-0.72

 Pagan

-0.70

 Garage

-0.70

Fal

-0.70

POSITIVE LOGITS

emia

1.19

ox

1.18

oxic

1.13

oxicity

1.07

osis

1.06

oxin

1.06

ogenic

1.05

 toxin

1.02

otyp

1.02

amide

1.01

Activations Density 0.186%

molecular or medical terms related to biological processes

terms associated with physiological processes and medical conditions

No Comments

No Known Activations