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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.07

3:0.07

4:0.08

5:0.08

6:0.08

7:0.07

8:0.09

9:0.09

10:0.08

11:0.08

Negative Logits

AP

-1.54

 rewards

-1.52

onson

-1.50

 rewarding

-1.49

rams

-1.48

Cu

-1.43

 sequences

-1.43

PD

-1.42

Vu

-1.40

 sequ

-1.39

POSITIVE LOGITS

soDeliveryDate

1.98

 advoc

1.96

Reviewer

1.94

░░

1.93

ャ

1.90

��

1.82

inion

1.71

 opin

1.70

 circumcision

1.69

◼

1.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.