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

0:0.08

1:0.08

2:0.07

3:0.08

4:0.08

5:0.09

6:0.09

7:0.09

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

 lect

-2.92

igham

-2.63

 gaze

-2.61

 Welch

-2.60

 strut

-2.51

lington

-2.50

rington

-2.48

steen

-2.43

 dial

-2.41

 endot

-2.38

POSITIVE LOGITS

 Mara

3.15

 Indones

2.92

 Siberian

2.77

.""

2.69

 Apollo

2.65

OA

2.64

onga

2.60

 Cambodia

2.59

 Sapp

2.58

andro

2.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.