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

0:0.06

1:0.12

2:0.07

3:0.08

4:0.09

5:0.07

6:0.07

7:0.07

8:0.08

9:0.09

10:0.09

11:0.07

Negative Logits

 Metropolitan

-1.83

 Oval

-1.66

 subway

-1.61

tab

-1.53

 preschool

-1.51

 Mechdragon

-1.50

sew

-1.49

 Stadium

-1.49

 prenatal

-1.47

 tube

-1.44

POSITIVE LOGITS

WARE

1.75

escription

1.69

OOOO

1.65

Released

1.64

ogenic

1.60

OOOOOOOO

1.60

FREE

1.59

Was

1.58

Synopsis

1.58

omsky

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.