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

0:0.07

1:0.07

2:0.08

3:0.07

4:0.09

5:0.09

6:0.08

7:0.07

8:0.08

9:0.06

10:0.09

11:0.08

Negative Logits

 numbering

-1.84

TextColor

-1.66

 numbered

-1.55

iform

-1.54

 numer

-1.51

 strikingly

-1.49

 inhib

-1.48

 brightest

-1.47

 differed

-1.46

 noteworthy

-1.45

POSITIVE LOGITS

milo

1.79

 yourself

1.65

 Yourself

1.61

package

1.59

 podcast

1.58

 Goes

1.57

morrow

1.56

 answ

1.52

 Explain

1.51

voice

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.