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

1:0.08

2:0.08

3:0.07

4:0.07

5:0.08

6:0.10

7:0.08

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

changes

-1.87

 Andersen

-1.68

 Meyer

-1.61

 Lerner

-1.58

¶

-1.54

 Dare

-1.52

 Framework

-1.52

Fram

-1.52

Zup

-1.50

Doe

-1.50

POSITIVE LOGITS

nikov

1.97

ecause

1.92

ategory

1.86

vertisement

1.84

arcity

1.80

ividual

1.79

obbies

1.73

aughs

1.71

tainment

1.70

senal

1.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.