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

0:0.08

1:0.07

2:0.09

3:0.08

4:0.07

5:0.08

6:0.07

7:0.06

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

 realities

-1.70

oi

-1.64

 mandates

-1.62

obs

-1.60

LG

-1.60

\-

-1.57

soType

-1.57

SPONSORED

-1.53

 Chapters

-1.50

ols

-1.49

POSITIVE LOGITS

ftime

1.97

illon

1.92

ezvous

1.90

Finish

1.80

Ped

1.78

 trek

1.77

Balt

1.74

WithNo

1.73

cellence

1.70

 Nose

1.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.