INDEX

Explanations

words associated with regulations and procedures

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

0:0.09

1:0.03

2:0.08

3:0.04

4:0.06

5:0.04

6:0.23

7:0.04

8:0.06

9:0.20

10:0.03

11:0.04

Negative Logits

Cook

-4.66

cook

-4.23

 Hansen

-4.05

esm

-4.03

tten

-3.98

 Roose

-3.95

onen

-3.73

 Melanie

-3.71

 Dickens

-3.70

 Wolves

-3.67

POSITIVE LOGITS

 Quad

9.18

 quad

8.53

quad

7.95

 triangle

5.90

 triangles

5.61

 Triangle

4.74

Tri

4.71

tri

4.52

 triangular

4.45

Tri

4.35

Activations Density 0.001%

words associated with regulations and procedures

No Comments

No Known Activations