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

1:0.08

2:0.09

3:0.07

4:0.10

5:0.07

6:0.06

7:0.08

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

merce

-2.19

ebted

-2.03

entimes

-1.87

ebin

-1.83

uilt

-1.79

 challeng

-1.76

glomer

-1.74

untarily

-1.71

iosyncr

-1.65

quartered

-1.65

POSITIVE LOGITS

wolf

1.71

��

1.60

 🙂

1.60

 understatement

1.57

 Orion

1.53

Availability

1.47

Reloaded

1.47

 Samson

1.46

 Sparks

1.45

 straw

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.