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

0:0.07

1:0.09

2:0.09

3:0.09

4:0.08

5:0.08

6:0.06

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

witch

-1.65

atin

-1.61

atri

-1.55

 decl

-1.52

idal

-1.50

orage

-1.47

apes

-1.41

isure

-1.40

isable

-1.36

ctions

-1.30

POSITIVE LOGITS

ONSORED

1.80

版

1.68

GGGGGGGG

1.68

═

1.66

 withd

1.62

 glim

1.51

EEEE

1.51

PDATE

1.45

etheless

1.43

AAAA

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.