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

2:0.09

3:0.08

4:0.07

5:0.07

6:0.08

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

orns

-1.68

 Prin

-1.64

 Sponsor

-1.63

 Tags

-1.62

 recipient

-1.60

azo

-1.58

aron

-1.57

paren

-1.57

ipples

-1.55

uer

-1.55

POSITIVE LOGITS

 Hitchcock

1.75

kaya

1.71

?'"

1.70

rium

1.62

icz

1.61

yi

1.60

rio

1.58

 Talent

1.57

 acted

1.55

 posterior

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.