INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.08

1:0.09

2:0.07

3:0.07

4:0.09

5:0.08

6:0.08

7:0.06

8:0.09

9:0.09

10:0.06

11:0.08

Negative Logits

rals

-1.74

merce

-1.71

iosyncr

-1.61

 respectively

-1.58

uph

-1.56

liners

-1.55

terms

-1.54

raltar

-1.53

brid

-1.53

eln

-1.53

POSITIVE LOGITS

 Narc

1.72

 Anthropology

1.68

 Cluster

1.58

 Clinical

1.57

 Instructor

1.54

 Hare

1.53

 Kelley

1.52

 Coch

1.50

 psychologist

1.48

 Robb

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.