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

2:0.07

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.09

9:0.08

10:0.08

11:0.09

Negative Logits

 redistributed

-1.76

TMZ

-1.67

 salts

-1.64

 extraction

-1.59

 withheld

-1.57

 Hert

-1.56

 fumes

-1.56

 postponed

-1.52

 strains

-1.51

 Singer

-1.50

POSITIVE LOGITS

DragonMagazine

2.15

 Occupations

1.95

 Attributes

1.87

onomy

1.84

 Interface

1.83

omon

1.75

itte

1.73

ieties

1.73

Commun

1.67

seless

1.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.