INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.09

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

byter

-3.10

��

-3.02

 practition

-2.88

qqa

-2.77

anus

-2.77

idelines

-2.73

sembly

-2.69

etsk

-2.67

idis

-2.63

 Pengu

-2.63

POSITIVE LOGITS

VERTISEMENT

2.93

 Walt

2.86

�

2.68

 Rated

2.62

—-

2.57

###

2.56

——

2.56

[[

2.54

 Frey

2.47

[[

2.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.