INDEX

Explanations

key terms associated with charges and legal matters

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

0:0.10

1:0.04

2:0.06

3:0.05

4:0.05

5:0.05

6:0.21

7:0.05

8:0.12

9:0.14

10:0.04

11:0.05

Negative Logits

 Venice

-4.17

 Bahamas

-4.05

 surfing

-3.70

 shrimp

-3.66

 Warwick

-3.56

 swim

-3.47

 Brune

-3.46

wick

-3.43

 yacht

-3.41

 seas

-3.41

POSITIVE LOGITS

ML

9.57

ML

7.94

ml

6.27

MLA

5.30

LL

4.96

MR

4.35

MR

4.24

 Lansing

3.91

ml

3.90

 Arrow

3.76

Activations Density 0.001%

key terms associated with charges and legal matters

No Comments

No Known Activations