INDEX

Explanations

legal and financial terms related to agreements and settlements

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

0:0.08

1:0.01

2:0.06

3:0.14

4:0.01

5:0.09

6:0.01

7:0.06

8:0.03

9:0.01

10:0.43

11:0.02

Negative Logits

 negatively

-2.18

aval

-2.15

earch

-2.14

 unlucky

-2.13

Reviewer

-2.10

 flock

-2.01

 quizz

-2.00

 haunted

-1.94

grave

-1.94

 envy

-1.91

POSITIVE LOGITS

 agreement

3.66

 agreed

2.99

 agreements

2.98

 truce

2.89

 concessions

2.88

 agreeing

2.84

 Agreement

2.83

reement

2.80

 compromise

2.77

 surrender

2.71

Activations Density 0.360%

legal and financial terms related to agreements and settlements

No Comments

No Known Activations