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

1:0.04

2:0.09

3:0.09

4:0.08

5:0.06

6:0.07

7:0.09

8:0.08

9:0.09

10:0.10

11:0.08

Negative Logits

 Ogre

-1.76

 Doodle

-1.70

 brill

-1.69

 Schwar

-1.57

 Blazers

-1.57

 shortened

-1.56

 Drawn

-1.53

 Maul

-1.52

 homage

-1.50

 Reloaded

-1.49

POSITIVE LOGITS

opath

1.97

icans

1.89

ploy

1.88

ican

1.80

iltration

1.79

ential

1.74

hari

1.73

quist

1.68

opathy

1.67

ilon

1.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.