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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.11

7:0.09

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

�

-1.71

Magn

-1.67

advertisement

-1.58

�

-1.52

court

-1.51

 entr

-1.49

Ven

-1.45

�

-1.42

 impetus

-1.41

zen

-1.41

POSITIVE LOGITS

ecause

1.97

erness

1.86

 Fault

1.72

htt

1.71

uphem

1.65

omorphic

1.64

Fas

1.59

ynes

1.57

 macros

1.56

*)

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.