INDEX

Explanations

specific segments or lists typically associated with media, such as members, tracks, or references related to music or films

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.06

1:0.05

2:0.05

3:0.08

4:0.35

5:0.06

6:0.03

7:0.07

8:0.07

9:0.02

10:0.06

11:0.05

Negative Logits

 BLACK

-3.67

 JOHN

-3.51

TWO

-3.49

 WHITE

-3.44

 ROCK

-3.41

 THREE

-3.41

HIS

-3.28

AMY

-3.24

 GREEN

-3.22

 GREAT

-3.20

POSITIVE LOGITS

Dialogue

3.49

Notes

3.45

Production

3.40

References

3.39

Notable

3.38

 Tracks

3.37

Usage

3.25

Availability

3.18

License

3.18

Links

3.18

Activations Density 0.093%

specific segments or lists typically associated with media, such as members, tracks, or references related to music or films

No Comments

No Known Activations