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

0:0.07

1:0.12

2:0.07

3:0.09

4:0.07

5:0.09

6:0.07

7:0.08

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

EngineDebug

-1.87

mia

-1.67

vil

-1.67

…)

-1.64

 exclaimed

-1.64

sided

-1.63

,,

-1.60

 totaled

-1.58

 fluct

-1.58

 cracked

-1.58

POSITIVE LOGITS

pse

2.10

�醒

1.93

 Beir

1.92

 Clifford

1.83

 behav

1.75

 adolesc

1.70

 Haram

1.68

 veter

1.68

 Joel

1.66

 charact

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.