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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.07

5:0.09

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 cycl

-1.58

 desp

-1.53

 thous

-1.51

 suffering

-1.48

acus

-1.48

 phantom

-1.46

 coastline

-1.44

 automation

-1.43

nas

-1.43

 Odyssey

-1.41

POSITIVE LOGITS

soever

1.98

SPONSORED

1.67

/-

1.65

ept

1.60

llular

1.53

aligned

1.53

 Extras

1.52

 Properties

1.50

Pg

1.50

poon

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.