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

1:0.04

2:0.10

3:0.09

4:0.08

5:0.08

6:0.08

7:0.08

8:0.06

9:0.09

10:0.07

11:0.09

Negative Logits

 unpublished

-1.93

urtle

-1.49

uscript

-1.48

 unspecified

-1.47

ousand

-1.47

 batches

-1.43

TBA

-1.39

 Finished

-1.37

Rai

-1.36

selage

-1.35

POSITIVE LOGITS

 actionGroup

2.17

DragonMagazine

1.93

1.81

iolet

1.77

taboola

1.70

 hinges

1.69

 fract

1.67

��

1.67

�

1.60

MpServer

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.