INDEX

Explanations

mentions of chronic medical conditions

oai_token-act-pair · gpt-3.5-turbo

references to chronic health conditions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/(

-1.06

ramid

-0.97

ertodd

-0.81

imates

-0.72

animous

-0.72

ansk

-0.72

imore

-0.71

Ĭ±

-0.70

uthor

-0.70

hammad

-0.69

POSITIVE LOGITS

led

0.95

 traumatic

0.86

ling

0.84

lers

0.79

 inflammation

0.78

 diseases

0.75

pain

0.75

 disease

0.75

 obstruct

0.71

 fatigue

0.71

Activations Density 0.034%

mentions of chronic medical conditions

references to chronic health conditions

No Comments

No Known Activations