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

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.09

7:0.09

8:0.08

9:0.06

10:0.08

11:0.08

Negative Logits

 congr

-1.96

 entrepreneurial

-1.63

 entrepreneurship

-1.52

 behavi

-1.48

 modeling

-1.46

 olive

-1.41

sle

-1.40

 Marion

-1.40

 workflow

-1.40

ynski

-1.40

POSITIVE LOGITS

locks

1.75

hement

1.61

bul

1.60

ptions

1.57

Mech

1.55

Hong

1.53

dict

1.52

caps

1.50

cern

1.50

Parts

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.