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

0:0.05

1:0.08

2:0.07

3:0.08

4:0.11

5:0.05

6:0.07

7:0.16

8:0.05

9:0.06

10:0.09

11:0.09

Negative Logits

 Anon

-1.67

hw

-1.55

 Sacred

-1.47

 Paste

-1.44

ANN

-1.43

orah

-1.42

 Electricity

-1.42

 venom

-1.41

Focus

-1.40

 Chrys

-1.36

POSITIVE LOGITS

 spons

1.71

 afford

1.70

iences

1.68

osponsors

1.63

 negoti

1.60

 climates

1.59

ocene

1.58

 latitude

1.58

ateral

1.57

outheast

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.