INDEX

Explanations

patterns related to television ratings and viewership statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.02

2:0.09

3:0.07

4:0.08

5:0.04

6:0.03

7:0.15

8:0.03

9:0.05

10:0.25

11:0.11

Negative Logits

purpose

-1.53

isel

-1.50

common

-1.42

jar

-1.39

cpp

-1.38

natureconservancy

-1.38

hig

-1.35

phan

-1.32

orem

-1.28

yles

-1.28

POSITIVE LOGITS

 ratings

1.67

 screenings

1.53

 Nationwide

1.47

 Stream

1.40

 theaters

1.38

 Ratings

1.38

 broadcasters

1.36

 rosters

1.32

 Ranked

1.31

 suspensions

1.29

Activations Density 0.002%

patterns related to television ratings and viewership statistics

No Comments

No Known Activations