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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.09

2:0.12

3:0.08

4:0.06

5:0.08

6:0.08

7:0.06

8:0.06

9:0.08

10:0.07

11:0.07

Negative Logits

ese

-2.00

rouse

-1.76

Pokémon

-1.63

sed

-1.57

RFC

-1.52

oyle

-1.51

comments

-1.49

ev

-1.48

iff

-1.48

FF

-1.47

POSITIVE LOGITS

ailability

1.75

 Petra

1.72

 Obst

1.63

 eleph

1.63

 Copenhagen

1.63

�

1.57

 earthqu

1.55

 Papa

1.54

FSA

1.53

 Pigs

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.