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

0:0.07

1:0.08

2:0.09

3:0.07

4:0.07

5:0.09

6:0.09

7:0.07

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

 ANGEL

-1.54

stock

-1.49

 unfocusedRange

-1.48

morph

-1.47

duty

-1.45

aband

-1.44

leaf

-1.43

otte

-1.41

letter

-1.41

 Warranty

-1.40

POSITIVE LOGITS

═

1.59

ISTORY

1.49

['

1.47

ista

1.46

BLIC

1.43

 egalitarian

1.42

":["

1.38

 Devices

1.38

�

1.37

ּ

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.