INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.07

2:0.10

3:0.07

4:0.08

5:0.08

6:0.07

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 Rivers

-1.75

 Eyes

-1.52

 Pont

-1.51

 Subway

-1.48

 Wings

-1.46

Hud

-1.43

 Twins

-1.43

 Ward

-1.43

 Flesh

-1.42

Cyn

-1.40

POSITIVE LOGITS

ゴン

2.00

ilib

1.92

ーティ

1.80

ibli

1.70

icol

1.70

ajo

1.67

DERR

1.63

icrobial

1.58

antha

1.50

ertodd

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.