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

1:0.07

2:0.07

3:0.09

4:0.09

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

Downloadha

-1.91

Ranked

-1.89

 steroids

-1.73

benefit

-1.73

 Personally

-1.71

 Franch

-1.70

milo

-1.68

opoly

-1.67

 Parables

-1.63

enegger

-1.59

POSITIVE LOGITS

hran

1.64

 volt

1.63

 guard

1.60

 pronunciation

1.53

uv

1.52

 wrap

1.51

 dexter

1.50

 Close

1.49

 guards

1.47

ancel

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.