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

1:0.07

2:0.09

3:0.07

4:0.08

5:0.10

6:0.07

7:0.07

8:0.08

9:0.06

10:0.08

11:0.08

Negative Logits

:{

-1.88

uri

-1.79

outhern

-1.78

atl

-1.70

asher

-1.70

ukong

-1.70

places

-1.69

forge

-1.68

uristic

-1.68

arin

-1.67

POSITIVE LOGITS

��

1.69

Fn

1.67

 peace

1.67

APP

1.66

 damage

1.66

 symmetry

1.54

ヴ

1.53

 airflow

1.51

 accuracy

1.50

 reading

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.