INDEX

Explanations

mentions of the name "Max" with varying degrees of intensity

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Max."

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

GROUND

-0.79

RECT

-0.71

wark

-0.69

alam

-0.68

CHO

-0.67

ADRA

-0.67

FORE

-0.65

keeper

-0.65

cipline

-0.65

bare

-0.64

POSITIVE LOGITS

imus

1.46

imil

1.28

imize

1.23

imal

1.02

ima

0.98

ims

0.93

imates

0.92

 Payne

0.91

itar

0.91

imen

0.89

Activations Density 0.013%

mentions of the name "Max" with varying degrees of intensity

mentions of the name "Max."

No Comments

No Known Activations