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

2:0.08

3:0.10

4:0.09

5:0.07

6:0.06

7:0.08

8:0.09

9:0.08

10:0.07

11:0.09

Negative Logits

please

-1.60

ommel

-1.55

 Admission

-1.53

ayers

-1.52

 pled

-1.50

thood

-1.44

ativity

-1.41

aughs

-1.39

 violated

-1.39

Ame

-1.38

POSITIVE LOGITS

oxy

1.62

ascript

1.60

ircraft

1.55

bal

1.53

letico

1.51

Fram

1.49

hap

1.49

-+-+

1.46

xus

1.44

typ

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.