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

0:0.09

1:0.10

2:0.08

3:0.08

4:0.08

5:0.07

6:0.07

7:0.08

8:0.09

9:0.06

10:0.08

11:0.06

Negative Logits

:#

-2.02

 Breaker

-1.85

:,

-1.84

FontSize

-1.79

 Colors

-1.75

endif

-1.75

��

-1.74

 Other

-1.70

 Higher

-1.65

EVA

-1.64

POSITIVE LOGITS

 keynote

1.63

 proposal

1.58

 manifesto

1.58

offer

1.57

CLA

1.55

arb

1.54

 appetite

1.52

 incentive

1.51

 parcel

1.45

aser

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.