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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.08

3:0.07

4:0.09

5:0.09

6:0.08

7:0.07

8:0.07

9:0.09

10:0.09

11:0.07

Negative Logits

ッド

-1.81

 ACTIONS

-1.80

alog

-1.71

aired

-1.68

atically

-1.67

ュ

-1.62

selage

-1.62

ae

-1.55

 scouts

-1.54

irc

-1.52

POSITIVE LOGITS

 certify

1.83

maxwell

1.83

NING

1.74

kamp

1.71

vernment

1.67

schild

1.67

Bang

1.63

bringer

1.63

tein

1.57

 GOODMAN

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.