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

1:0.06

2:0.08

3:0.09

4:0.09

5:0.09

6:0.06

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

apego

-1.82

ocaust

-1.68

etheless

-1.66

 scapego

-1.64

 discrim

-1.64

otomy

-1.61

 wiret

-1.61

ocal

-1.60

 DeVos

-1.59

 Leone

-1.56

POSITIVE LOGITS

sun

1.92

reet

1.70

ourning

1.68

Prince

1.65

Fall

1.64

antha

1.59

Winter

1.56

ittens

1.55

venants

1.55

inches

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.