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

1:0.06

2:0.08

3:0.09

4:0.08

5:0.07

6:0.09

7:0.08

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

¶

-1.71

foundation

-1.54

──

-1.53

techn

-1.53

%:

-1.41

querade

-1.39

 wreckage

-1.38

 cables

-1.38

conservancy

-1.37

 resil

-1.37

POSITIVE LOGITS

channelAvailability

1.69

anan

1.68

 Topic

1.53

 Hume

1.50

sf

1.42

itious

1.40

 adul

1.39

 paternal

1.38

Issue

1.38

 Date

1.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.