INDEX

Explanations

No Explanations Found

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

1:0.07

2:0.08

3:0.09

4:0.10

5:0.06

6:0.08

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

umers

-3.05

 jars

-2.88

sylv

-2.82

 purch

-2.81

 reck

-2.77

 inquest

-2.75

 stockp

-2.74

 boycott

-2.67

Mach

-2.65

 stalk

-2.61

POSITIVE LOGITS

 Compass

3.21

AH

3.18

 Apache

3.10

 Wikimedia

3.02

CRC

3.02

️

2.95

2.93

��

2.88

2.87

2.78

Activations Density 0.000%

No Known Activations

This feature has no known activations.