INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.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

1:0.10

2:0.08

3:0.07

4:0.07

5:0.10

6:0.08

7:0.07

8:0.08

9:0.06

10:0.08

11:0.08

Negative Logits

efe

-1.91

Dup

-1.79

alsh

-1.74

aimon

-1.71

mans

-1.64

CBC

-1.63

CBC

-1.61

 Greenberg

-1.57

 Herz

-1.57

 MacDonald

-1.57

POSITIVE LOGITS

thumbnails

1.91

worldly

1.84

goers

1.77

 cliff

1.74

 lava

1.62

ftime

1.61

*/(

1.57

taboola

1.57

window

1.57

 WATCHED

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.