INDEX

Explanations

No Explanations Found

New Auto-Interp

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

0:0.07

1:0.05

2:0.08

3:0.09

4:0.09

5:0.07

6:0.08

7:0.10

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

 earthquakes

-1.65

 possibility

-1.59

idates

-1.58

 Cooke

-1.53

Lod

-1.50

 reactions

-1.49

 antidepressant

-1.47

Ry

-1.46

 reacted

-1.45

witch

-1.40

POSITIVE LOGITS

unes

2.12

)</

2.07

ilo

1.97

[|

1.92

hered

1.89

cu

1.77

aci

1.67

license

1.58

yright

1.58

arc

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.