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

0:0.07

1:0.05

2:0.08

3:0.08

4:0.08

5:0.08

6:0.09

7:0.07

8:0.07

9:0.09

10:0.09

11:0.08

Negative Logits

=-=-=-=-

-1.65

alog

-1.65

spection

-1.64

division

-1.62

beta

-1.55

incial

-1.54

alogy

-1.51

hran

-1.50

yards

-1.48

itations

-1.47

POSITIVE LOGITS

Madison

1.70

 volunte

1.69

 TODAY

1.61

 Marketable

1.44

 issuer

1.40

 thanked

1.39

 adam

1.37

 cher

1.35

 celeb

1.33

 ILCS

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.