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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

uyomi

-1.78

 Shades

-1.62

senal

-1.62

ioxide

-1.59

 Collider

-1.59

 Initiative

-1.58

 Pledge

-1.56

 Taxes

-1.55

 HSBC

-1.54

GW

-1.54

POSITIVE LOGITS

quit

1.85

bred

1.74

mode

1.70

ynchronous

1.68

hered

1.67

run

1.64

sleep

1.62

runs

1.61

ateurs

1.58

))))

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.