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

0:0.08

1:0.09

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

ozyg

-1.45

assic

-1.39

 prelim

-1.34

 Regist

-1.34

rants

-1.29

illin

-1.28

 tuberculosis

-1.26

idas

-1.24

oped

-1.24

breaks

-1.24

POSITIVE LOGITS

��

1.67

 Airl

1.57

 contingent

1.56

 Hezbollah

1.52

lance

1.50

 dehuman

1.36

 Beir

1.35

 acronym

1.33

 Bosnia

1.33

 Buckley

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.