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

1:0.11

2:0.07

3:0.08

4:0.07

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

igation

-1.71

ulated

-1.70

 Hearing

-1.65

atche

-1.64

=#

-1.62

cheon

-1.61

 Bern

-1.58

 Deadline

-1.56

�

-1.56

eland

-1.53

POSITIVE LOGITS

artifacts

1.72

 constitu

1.68

 weap

1.67

イト

1.63

 volunt

1.59

 reperto

1.58

 lifes

1.57

 welf

1.55

amily

1.55

 behav

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.