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

2:0.08

3:0.08

4:0.08

5:0.09

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

reci

-2.85

 Chili

-2.64

��

-2.63

 Intro

-2.56

Apps

-2.55

Kit

-2.53

Simple

-2.49

 Differences

-2.31

 Streets

-2.31

Interstitial

-2.27

POSITIVE LOGITS

\",

3.10

arial

2.73

\"

2.70

 scept

2.66

kus

2.63

 pseud

2.60

 Ange

2.57

\":

2.53

 thyroid

2.47

\"

2.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.