INDEX

Explanations

mentions of the term "Kind" often associated with different contexts and content

oai_token-act-pair · gpt-3.5-turbo

references to "Kindles" and related products or features

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

è¦ļéĨĴ

-0.88

Downloadha

-0.80

apons

-0.77

VEL

-0.75

IVER

-0.73

pez

-0.72

berus

-0.71

UNCH

-0.70

ZI

-0.70

ptions

-0.67

POSITIVE LOGITS

ness

1.08

hearted

0.96

ening

0.94

ened

0.91

erman

0.91

liness

0.88

red

0.88

leness

0.88

ling

0.84

elf

0.82

Activations Density 0.022%

mentions of the term "Kind" often associated with different contexts and content

references to "Kindles" and related products or features

No Comments

No Known Activations