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

1:0.06

2:0.08

3:0.08

4:0.10

5:0.08

6:0.10

7:0.08

8:0.09

9:0.07

10:0.07

11:0.07

Negative Logits

 Ruler

-2.05

 Dull

-1.85

 Migration

-1.80

 Mahjong

-1.75

ascript

-1.72

soft

-1.71

 Slave

-1.66

 Manip

-1.59

 Lumpur

-1.58

 Appearance

-1.55

POSITIVE LOGITS

hof

1.98

VILLE

1.69

 library

1.67

 boutique

1.64

 benefited

1.60

ooter

1.60

 deserving

1.58

ione

1.58

NI

1.57

iverse

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.