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

1:0.06

2:0.09

3:0.09

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

folios

-2.03

 Instr

-1.79

helps

-1.75

Tube

-1.71

 Comments

-1.70

 Sites

-1.67

 Lists

-1.63

leeve

-1.62

 Tube

-1.60

 Letters

-1.60

POSITIVE LOGITS

 sluggish

1.81

 destiny

1.80

 swift

1.78

 miracle

1.77

 strang

1.75

 promise

1.72

 comprom

1.71

 resolve

1.68

 paralysis

1.67

 goal

1.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.