INDEX

Explanations

words related to laws, enforcement, and proper roles in various contexts

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.37

1:0.04

2:0.01

3:0.12

4:0.09

5:0.09

6:0.04

7:0.02

8:0.09

9:0.05

10:0.02

11:0.02

Negative Logits

 unanimous

-1.43

theless

-1.43

izabeth

-1.42

laugh

-1.38

 Crosby

-1.38

Ic

-1.37

 fame

-1.34

 surprising

-1.32

 Lilly

-1.31

 whom

-1.30

POSITIVE LOGITS

iquette

1.73

 procedures

1.71

Management

1.69

�

1.65

 etiquette

1.62

 vetting

1.60

ogy

1.60

 stewards

1.59

 evaluation

1.58

urgy

1.55

Activations Density 0.005%

words related to laws, enforcement, and proper roles in various contexts

No Comments

No Known Activations