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

0:0.09

1:0.07

2:0.08

3:0.07

4:0.07

5:0.09

6:0.08

7:0.07

8:0.08

9:0.06

10:0.09

11:0.09

Negative Logits

selves

-1.95

AGES

-1.71

士

-1.70

chairs

-1.69

エル

-1.66

heads

-1.64

 derivatives

-1.64

π

-1.63

"]=>

-1.61

ヘラ

-1.58

POSITIVE LOGITS

ginx

1.67

 GoPro

1.65

 perk

1.63

tch

1.61

anyon

1.59

acha

1.58

 fireball

1.52

 Avatar

1.52

 beck

1.50

 cool

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.