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

0:0.07

1:0.08

2:0.08

3:0.07

4:0.09

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

cend

-1.69

sed

-1.63

roma

-1.59

Global

-1.58

tions

-1.58

ojure

-1.55

ndra

-1.50

EMENT

-1.47

ilight

-1.46

inka

-1.45

POSITIVE LOGITS

YA

1.61

 Yard

1.56

1.48

aan

1.48

���

1.47

¶

1.47

luck

1.41

�

1.41

 Bucks

1.39

got

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.