INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.07

3:0.07

4:0.08

5:0.09

6:0.09

7:0.08

8:0.07

9:0.08

10:0.08

11:0.10

Negative Logits

incent

-1.60

ntil

-1.59

 lapt

-1.56

 mosqu

-1.50

tu

-1.49

 registrations

-1.46

artifacts

-1.45

userc

-1.44

intern

-1.44

undai

-1.43

POSITIVE LOGITS

 Jericho

1.75

 Levin

1.60

 HuffPost

1.45

 Brock

1.44

 Cyber

1.44

LTD

1.41

 Shadows

1.41

 Clancy

1.40

 Leth

1.40

 Trog

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.