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

0:0.07

1:0.08

2:0.09

3:0.07

4:0.09

5:0.08

6:0.08

7:0.09

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

Zar

-2.96

ayne

-2.91

dream

-2.75

TPP

-2.68

 Dream

-2.67

enges

-2.61

boss

-2.59

arks

-2.58

 Schwar

-2.53

 Donetsk

-2.50

POSITIVE LOGITS

 uncovered

2.61

ecd

2.60

 unearthed

2.51

 compiled

2.50

 compiling

2.48

 trunc

2.47

dig

2.46

 documenting

2.40

 anecd

2.40

 archae

2.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.