INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

1:0.07

2:0.08

3:0.07

4:0.08

5:0.09

6:0.09

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

izabeth

-1.59

 Rapt

-1.46

ignt

-1.44

tnc

-1.41

washer

-1.41

wr

-1.40

 hers

-1.39

flies

-1.37

rium

-1.35

pur

-1.34

POSITIVE LOGITS

━

1.58

ahoo

1.56

 WATCHED

1.53

actionDate

1.49

URRENT

1.47

:'

1.45

OFF

1.44

IRED

1.40

ESE

1.36

Published

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.