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

1:0.05

2:0.08

3:0.07

4:0.07

5:0.09

6:0.08

7:0.09

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

mast

-2.00

emetery

-1.80

ommel

-1.80

strument

-1.79

ategory

-1.78

ildo

-1.78

mercial

-1.74

utic

-1.69

orable

-1.68

plet

-1.65

POSITIVE LOGITS

Pyr

1.79

 Quinn

1.74

 Sheldon

1.74

QC

1.62

 Arbit

1.61

 Shapiro

1.59

 Bram

1.58

ONT

1.57

 Mand

1.53

 Morgan

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.