INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

1:0.09

2:0.08

3:0.07

4:0.08

5:0.09

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

asus

-1.59

behind

-1.50

missing

-1.45

sted

-1.45

 registrations

-1.45

warning

-1.44

 Inspection

-1.44

undai

-1.42

orsi

-1.41

 reopened

-1.36

POSITIVE LOGITS

 fancy

1.44

 stereotype

1.44

 trendy

1.41

 cove

1.40

 stereotypes

1.37

 cliché

1.32

redients

1.32

 Sodium

1.30

arcity

1.29

 metaphors

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.