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

3:0.08

4:0.09

5:0.07

6:0.08

7:0.09

8:0.06

9:0.08

10:0.07

11:0.08

Negative Logits

 mentally

-1.51

 gamble

-1.46

expensive

-1.44

 Sheldon

-1.43

 trusting

-1.42

 サーティワン

-1.42

���

-1.37

 clipboard

-1.37

Phys

-1.36

 awhile

-1.36

POSITIVE LOGITS

 Voices

1.83

ategories

1.83

entimes

1.70

 Peaks

1.65

ingo

1.63

omas

1.59

ersed

1.59

 Topics

1.55

halla

1.55

 "$:/

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.