INDEX

Explanations

words related to Smart TVs and their features

oai_token-act-pair · gpt-3.5-turbo

references to smart TVs and related devices

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

0000000000000000

-0.76

 repr

-0.74

staking

-0.73

ussen

-0.71

tti

-0.67

 Yates

-0.66

cies

-0.66

onies

-0.66

00000000

-0.65

 repeated

-0.64

POSITIVE LOGITS

TVs

1.02

 Roku

0.95

 Everywhere

0.81

ILLE

0.79

 router

0.77

 Streaming

0.77

ecast

0.77

 Kodi

0.76

 Shows

0.76

Plex

0.76

Activations Density 0.027%

words related to Smart TVs and their features

references to smart TVs and related devices

No Comments

No Known Activations