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

1:0.09

2:0.07

3:0.06

4:0.08

5:0.08

6:0.10

7:0.08

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

 optimizations

-1.51

hesda

-1.47

 invalid

-1.45

ecided

-1.43

 factors

-1.42

atibility

-1.41

 Factors

-1.33

 configurations

-1.31

 intervening

-1.31

 assignment

-1.30

POSITIVE LOGITS

️

1.87

ulic

1.64

↵

1.59

alach

1.52

1.50

神

1.48

 Winc

1.46

 サーティワン

1.46

pressed

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.