INDEX

Explanations

the name "Max" specifically, especially with a high activation value

oai_token-act-pair · gpt-3.5-turbo

the name "Max" in various contexts

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

GROUND

-0.82

RECT

-0.80

alam

-0.78

cipline

-0.77

keeper

-0.74

wark

-0.71

CHO

-0.70

soType

-0.69

velt

-0.69

taboola

-0.69

POSITIVE LOGITS

imus

1.42

imil

1.23

imize

1.17

 Payne

1.01

imal

1.01

ima

0.95

itar

0.94

imates

0.91

imen

0.86

ims

0.85

Activations Density 0.010%

the name "Max" specifically, especially with a high activation value

the name "Max" in various contexts

No Comments

No Known Activations