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

0:0.09

1:0.07

2:0.08

3:0.07

4:0.09

5:0.09

6:0.06

7:0.07

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

──

-1.69

idges

-1.60

*)

-1.58

◼

-1.57

otte

-1.54

#$

-1.50

â

-1.48

��

-1.44

 indirectly

-1.43

 Tate

-1.42

POSITIVE LOGITS

quickShipAvailable

2.10

BuyableInstoreAndOnline

1.69

wild

1.67

 retirement

1.66

ateful

1.65

 srfAttach

1.46

 primitive

1.44

 grounding

1.44

 demos

1.41

aunts

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.