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

3:0.08

4:0.08

5:0.07

6:0.08

7:0.09

8:0.08

9:0.06

10:0.08

11:0.08

Negative Logits

ciating

-1.72

quickShipAvailable

-1.65

-1.60

vine

-1.60

pmwiki

-1.52

 poking

-1.50

 analys

-1.47

gul

-1.45

 BALL

-1.43

 sucker

-1.43

POSITIVE LOGITS

amily

1.79

ements

1.67

uctions

1.61

 Sirius

1.60

 generations

1.59

 Generations

1.56

aea

1.54

ribes

1.54

 Presidency

1.54

 families

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.