INDEX

Explanations

words related to instant products or processes

oai_token-act-pair · gpt-3.5-turbo

references to "instant" products or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

llah

-0.78

umbing

-0.77

^^^^

-0.68

ALD

-0.66

 Seeking

-0.63

ramids

-0.63

atche

-0.62

MIC

-0.62

tnc

-0.62

avid

-0.61

POSITIVE LOGITS

aneously

2.14

aneous

1.63

 gratification

1.53

iation

1.40

iated

1.37

iations

1.36

iating

1.29

iate

1.25

iates

1.12

 replay

1.08

Activations Density 0.022%

words related to instant products or processes

references to "instant" products or experiences

No Comments

No Known Activations