INDEX

Explanations

words related to credentials or official recognition

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of "red."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

oteric

-0.69

SPONSORED

-0.67

OTOS

-0.67

Â·Â·

-0.65

renheit

-0.64

enegger

-0.62

hang

-0.62

OHN

-0.62

 Luthor

-0.61

POSITIVE LOGITS

uced

1.35

eem

1.18

irect

1.17

ucing

1.15

uces

1.11

ding

1.09

uce

1.03

icative

1.03

emption

1.03

uctive

1.01

Activations Density 0.022%

words related to credentials or official recognition

terms related to the concept of "red."

No Comments

No Known Activations