INDEX

Explanations

phrases related to maintaining calmness or peacefulness

oai_token-act-pair · gpt-3.5-turbo

references to a sense of calmness or tranquility

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

ographies

-0.75

hester

-0.73

OGR

-0.72

rocket

-0.69

ammy

-0.69

fruit

-0.65

ADA

-0.64

iosyncr

-0.64

 Sins

-0.63

 Parenthood

-0.63

POSITIVE LOGITS

 calm

1.06

ness

0.97

 demeanor

0.90

erate

0.85

est

0.82

escal

0.81

 calming

0.79

 Calm

0.77

 partName

0.77

zers

0.77

Activations Density 0.016%

phrases related to maintaining calmness or peacefulness

references to a sense of calmness or tranquility

No Comments

No Known Activations