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

1:0.05

2:0.08

3:0.08

4:0.09

5:0.08

6:0.08

7:0.08

8:0.10

9:0.08

10:0.07

11:0.08

Negative Logits

 unanswered

-1.81

-1.60

 aside

-1.56

 apprehens

-1.50

 margins

-1.49

 inaction

-1.47

upon

-1.46

 unsolved

-1.44

 unresolved

-1.42

 sensitivity

-1.41

POSITIVE LOGITS

igun

1.87

ufact

1.68

 pestic

1.66

miah

1.65

zsche

1.63

izoph

1.60

itect

1.59

dinand

1.59

 agre

1.57

 spons

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.