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

Head Attr Weights

0:0.07

1:0.07

2:0.09

3:0.09

4:0.08

5:0.07

6:0.08

7:0.08

8:0.09

9:0.07

10:0.07

11:0.09

Negative Logits

allery

-1.79

abases

-1.73

ça

-1.65

sembly

-1.60

heng

-1.59

rices

-1.57

phabet

-1.54

rongh

-1.53

iae

-1.53

urtles

-1.52

POSITIVE LOGITS

Spoiler

1.77

ADVERTISEMENT

1.74

 parap

1.72

Come

1.61

aimon

1.60

...?

1.60

 behavi

1.56

っ

1.54

https

1.54

........

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.