INDEX

Explanations

information related to movies and TV shows, particularly those available for streaming on platforms like Netflix and Amazon Prime

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

mentions of streaming services, especially Netflix

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.05

2:0.20

3:0.09

4:0.05

5:0.07

6:0.03

7:0.04

8:0.03

9:0.21

10:0.08

11:0.03

Negative Logits

alin

-1.25

eric

-1.21

rious

-1.21

ofi

-1.19

oran

-1.16

ottesville

-1.15

zbek

-1.14

ayne

-1.13

onian

-1.11

osi

-1.11

POSITIVE LOGITS

 Gleaming

1.43

 Channel

1.32

Movie

1.30

 Streaming

1.27

 Bravo

1.26

 Serie

1.26

 Premiere

1.25

 Movie

1.25

 Brav

1.24

Channel

1.23

Activations Density 0.012%

information related to movies and TV shows, particularly those available for streaming on platforms like Netflix and Amazon Prime

mentions of streaming services, especially Netflix

No Comments

No Known Activations