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

0:0.08

1:0.09

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

ukong

-1.79

+/-

-1.72

*/(

-1.72

yip

-1.59

神

-1.57

apesh

-1.55

Fei

-1.51

GGGG

-1.50

POV

-1.49

Pinterest

-1.48

POSITIVE LOGITS

road

1.78

alloc

1.69

ements

1.67

olid

1.66

olicy

1.64

lishing

1.58

acks

1.56

omics

1.52

 loader

1.50

 Elementary

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.