INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.07

1:0.08

2:0.08

3:0.09

4:0.07

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

:/

-2.79

 Schultz

-2.75

eka

-2.71

minent

-2.71

isconsin

-2.62

NRS

-2.57

 Rabbi

-2.53

 Offic

-2.52

Spe

-2.50

 Rasmussen

-2.50

POSITIVE LOGITS

 recycled

3.42

 recycle

3.27

 reuse

3.12

 reused

2.97

 upgrades

2.85

 bomb

2.78

 animations

2.76

 reusable

2.74

 recycling

2.66

 inciner

2.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.