INDEX

Explanations

words related to emotional stoicism

oai_token-act-pair · gpt-3.5-turbo

instances of the word "stoic" and its variations, indicating a focus on emotional restraint or lack of expression

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

 Pathfinder

-0.72

URI

-0.72

 Horizons

-0.72

 Odyssey

-0.68

URR

-0.67

 recall

-0.67

HCR

-0.66

ATA

-0.63

ÙĪ

-0.63

displayText

-0.63

POSITIVE LOGITS

pper

1.31

ppy

1.23

pped

1.20

pping

1.15

ppers

1.11

ven

0.96

ops

0.95

uber

0.95

iety

0.94

ppings

0.94

Activations Density 0.018%

words related to emotional stoicism

instances of the word "stoic" and its variations, indicating a focus on emotional restraint or lack of expression

No Comments

No Known Activations