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

1:0.04

2:0.09

3:0.07

4:0.09

5:0.07

6:0.07

7:0.08

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

ⓘ

-2.10

』

-1.90

 Maid

-1.78

 Babel

-1.76

の魔

-1.72

 trope

-1.67

ヘラ

-1.64

�

-1.61

 Afric

-1.61

ⓘ

-1.59

POSITIVE LOGITS

 retina

1.95

 sockets

1.95

 socket

1.73

 recovered

1.66

eele

1.66

iliated

1.59

 retweet

1.58

 supporter

1.57

 screenshot

1.55

Latest

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.