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

0:0.07

1:0.07

2:0.08

3:0.10

4:0.09

5:0.07

6:0.09

7:0.09

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

nda

-2.09

ovo

-1.86

dot

-1.79

liv

-1.76

contin

-1.75

zb

-1.72

 Sched

-1.71

ubs

-1.71

rone

-1.70

ni

-1.69

POSITIVE LOGITS

 educate

1.92

 immersed

1.86

 architect

1.73

 educated

1.71

 philanthrop

1.67

 devote

1.67

 firsthand

1.65

 careful

1.63

 leap

1.63

 educating

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.