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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.07

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.06

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

urst

-1.91

Zip

-1.82

 Finder

-1.79

 equivalents

-1.79

 Spotify

-1.75

flix

-1.75

 Dropbox

-1.74

cigarettes

-1.64

 Tiff

-1.61

fruit

-1.60

POSITIVE LOGITS

ady

1.85

Commun

1.59

 Bosnia

1.58

 Peoples

1.56

 kidding

1.52

 sorcery

1.50

untled

1.50

 euth

1.50

itsch

1.47

 COMMUN

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.