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

0:0.08

1:0.06

2:0.07

3:0.09

4:0.08

5:0.06

6:0.09

7:0.08

8:0.09

9:0.08

10:0.08

11:0.09

Negative Logits

wcsstore

-1.90

actionDate

-1.85

ッド

-1.81

 referen

-1.75

ZX

-1.68

 insepar

-1.68

quote

-1.65

黒

-1.65

 legality

-1.60

Benz

-1.58

POSITIVE LOGITS

marg

1.81

 indicated

1.59

etermined

1.47

Pod

1.45

 irrad

1.42

ember

1.42

eta

1.41

orks

1.39

>(

1.39

ieving

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.