INDEX

Explanations

words related to communication or connection between entities

oai_token-act-pair · gpt-3.5-turbo

terms related to interaction and engagement

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

peria

-0.77

prus

-0.73

ciples

-0.72

ussy

-0.71

zn

-0.71

haps

-0.70

cott

-0.69

enthal

-0.67

conservancy

-0.66

aft

-0.65

POSITIVE LOGITS

ivity

0.99

 interactions

0.98

 interaction

0.91

ively

0.88

ually

0.87

iences

0.86

uate

0.83

ships

0.80

uality

0.78

halla

0.78

Activations Density 0.022%

words related to communication or connection between entities

terms related to interaction and engagement

No Comments

No Known Activations