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

1:0.06

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

 Mehran

-1.65

 Gupta

-1.59

 Klux

-1.59

 Johannes

-1.53

 literacy

-1.50

iewicz

-1.50

 Cheong

-1.49

 arsen

-1.49

 Hath

-1.48

 Penet

-1.47

POSITIVE LOGITS

 confir

1.77

fab

1.61

displayText

1.60

rights

1.58

secure

1.57

rules

1.55

loving

1.54

src

1.54

approved

1.53

rr

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.