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

0:0.09

1:0.06

2:0.08

3:0.09

4:0.09

5:0.08

6:0.08

7:0.07

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

 Hover

-1.81

 Burr

-1.63

 Berks

-1.61

onnaissance

-1.61

stration

-1.60

 thumbs

-1.58

 shrug

-1.55

 courage

-1.54

 clicks

-1.49

 Actions

-1.48

POSITIVE LOGITS

interstitial

1.88

DIV

1.70

exclusive

1.69

proclaimed

1.67

famous

1.67

 endowed

1.66

Asia

1.66

 gifted

1.57

 migrant

1.55

uca

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.