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

0:0.08

1:0.05

2:0.09

3:0.08

4:0.09

5:0.08

6:0.08

7:0.07

8:0.07

9:0.09

10:0.09

11:0.07

Negative Logits

lie

-1.62

hen

-1.48

SPONSORED

-1.47

sed

-1.45

Scy

-1.42

 Hulu

-1.40

igne

-1.38

obin

-1.36

Fox

-1.34

bull

-1.33

POSITIVE LOGITS

APS

1.73

ADRA

1.72

ccording

1.69

ARC

1.63

 Registrar

1.61

asus

1.60

Applications

1.59

respective

1.59

uberty

1.55

 enthusi

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.