INDEX

Explanations

concepts related to tolerance and open-mindedness

oai_token-act-pair · gpt-3.5-turbo

concepts and discussions around tolerance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

prints

-0.74

tein

-0.71

vet

-0.66

silver

-0.66

grave

-0.64

ramid

-0.63

cpu

-0.63

gin

-0.62

onne

-0.62

joining

-0.62

POSITIVE LOGITS

 tolerance

1.27

 tolerant

1.10

olerance

1.06

 intolerance

1.05

 toler

0.96

 intoler

0.95

 tolerate

0.84

terness

0.79

ophobia

0.77

 sensitivity

0.75

Activations Density 0.009%

concepts related to tolerance and open-mindedness

concepts and discussions around tolerance in various contexts

No Comments

No Known Activations