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

0:0.06

1:0.06

2:0.08

3:0.07

4:0.09

5:0.07

6:0.10

7:0.08

8:0.08

9:0.07

10:0.10

11:0.08

Negative Logits

acea

-1.82

agn

-1.76

changing

-1.73

ヤ

-1.69

aces

-1.65

changes

-1.65

ageddon

-1.64

filled

-1.60

angered

-1.57

changed

-1.55

POSITIVE LOGITS

Fn

1.58

))))

1.54

 supervised

1.51

 WATCHED

1.51

 playthrough

1.49

 surv

1.48

 operator

1.46

 unit

1.42

¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯

1.41

 airflow

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.