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

1:0.11

2:0.07

3:0.08

4:0.08

5:0.06

6:0.09

7:0.09

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

contact

-1.74

tee

-1.46

prom

-1.45

Solid

-1.44

 lair

-1.43

 Ukrain

-1.43

 elect

-1.39

HQ

-1.39

erie

-1.37

Site

-1.36

POSITIVE LOGITS

haar

1.86

lees

1.67

gart

1.67

Pew

1.60

umerable

1.56

paces

1.55

ertation

1.54

rencies

1.52

Obj

1.50

 Cups

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.