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

0:0.08

1:0.08

2:0.08

3:0.09

4:0.08

5:0.07

6:0.09

7:0.07

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

estine

-1.54

 rationality

-1.53

idates

-1.52

 maximal

-1.50

idepress

-1.48

 civilisation

-1.47

 superiority

-1.46

 behaviours

-1.45

 correctness

-1.44

bps

-1.41

POSITIVE LOGITS

taboola

1.87

PHOTOS

1.82

Rue

1.75

生

1.64

BuyableInstoreAndOnline

1.62

NEY

1.61

 Deadline

1.58

neau

1.55

------

1.54

 Revenue

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.