INDEX

Explanations

phrases containing the word "us"

oai_token-act-pair · gpt-3.5-turbo

references to assistance and direction in a context involving authority figures or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

oard

-0.79

prison

-0.76

rals

-0.70

aband

-0.69

sec

-0.67

col

-0.67

ipolar

-0.67

celer

-0.66

reen

-0.66

readable

-0.65

POSITIVE LOGITS

ï¸ı

0.78

AMA

0.65

 ACPI

0.61

WIN

0.61

ournals

0.61

Mig

0.60

 Grow

0.59

è¯

0.59

 wart

0.59

 mars

0.58

Activations Density 0.000%

phrases containing the word "us"

references to assistance and direction in a context involving authority figures or organizations

No Comments

No Known Activations