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

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

 substitutes

-1.77

 Orig

-1.70

ufact

-1.62

 abolished

-1.59

 experimented

-1.55

emporary

-1.52

 specimens

-1.47

 compositions

-1.46

 exists

-1.46

Tsu

-1.46

POSITIVE LOGITS

cause

1.66

 dismay

1.65

wear

1.60

Balt

1.59

reply

1.59

DAM

1.59

 sophomore

1.58

_>

1.57

Joined

1.56

iddy

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.