INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

1:0.09

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.07

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

Room

-2.79

batch

-2.61

HIP

-2.55

 Cosponsors

-2.51

shapeshifter

-2.48

 Route

-2.48

�

-2.47

ipl

-2.46

��

-2.44

sth

-2.43

POSITIVE LOGITS

 Anarch

2.86

 brill

2.80

 Medieval

2.75

 sentimental

2.75

 tyres

2.71

 Riot

2.71

 Zoro

2.70

 anarchism

2.69

 Tolkien

2.57

xual

2.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.