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

1:0.09

2:0.08

3:0.08

4:0.07

5:0.08

6:0.07

7:0.07

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

rows

-1.59

rieved

-1.59

bage

-1.52

lear

-1.49

natureconservancy

-1.48

earch

-1.48

rendered

-1.45

AAAAAAAA

-1.45

rontal

-1.43

abo

-1.41

POSITIVE LOGITS

BuyableInstoreAndOnline

2.02

 Antar

1.73

 financing

1.70

 Marketable

1.66

 indemn

1.60

��極

1.56

netflix

1.55

 alike

1.47

actionDate

1.42

 Lauder

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.