INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

2:0.07

3:0.09

4:0.09

5:0.08

6:0.08

7:0.08

8:0.07

9:0.07

10:0.09

11:0.07

Negative Logits

asty

-2.72

chance

-2.65

md

-2.64

mac

-2.61

mit

-2.60

raft

-2.59

 Junk

-2.51

ulture

-2.49

ump

-2.47

morning

-2.42

POSITIVE LOGITS

 Municipal

2.80

 Arpaio

2.76

 Toledo

2.70

Fram

2.68

 prosec

2.67

 Contra

2.63

 Tammy

2.61

 Alvarez

2.59

 Saras

2.58

SV

2.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.