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

0:0.08

1:0.04

2:0.10

3:0.09

4:0.07

5:0.08

6:0.06

7:0.09

8:0.08

9:0.07

10:0.08

11:0.10

Negative Logits

 Machines

-1.70

 semantics

-1.64

vas

-1.61

 Apart

-1.60

 Following

-1.57

 continuity

-1.55

etc

-1.52

��

-1.51

 grievances

-1.49

 Personally

-1.48

POSITIVE LOGITS

erity

2.30

eday

2.10

 Prescott

2.02

eger

1.91

illion

1.90

handler

1.80

ounter

1.77

bnb

1.75

ometimes

1.75

ainment

1.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.