INDEX

Explanations

words related to medical conditions and treatments concerning the brain

oai_token-act-pair · gpt-3.5-turbo

references to the brain and its conditions or attributes

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

 Bundy

-0.70

 impunity

-0.67

Dialog

-0.66

adoes

-0.66

 Arabia

-0.64

 FANTASY

-0.64

 Bowie

-0.64

inen

-0.64

 Yanuk

-0.63

 Faust

-0.61

POSITIVE LOGITS

stem

1.35

washed

1.27

washing

1.18

wash

1.12

iac

1.00

waves

0.95

caps

0.94

fuck

0.91

storms

0.85

cap

0.84

Activations Density 0.024%

words related to medical conditions and treatments concerning the brain

references to the brain and its conditions or attributes

No Comments

No Known Activations