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

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 サーティワン

-1.96

 alike

-1.92

 adherent

-1.88

USE

-1.73

isters

-1.70

afety

-1.66

 promul

-1.65

icrobial

-1.64

 prote

-1.62

 therape

-1.59

POSITIVE LOGITS

yout

1.75

jog

1.75

enza

1.75

 srfAttach

1.73

skip

1.71

 Verse

1.69

��

1.67

JV

1.66

 Polo

1.65

wav

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.