INDEX

Explanations

phrases that indicate status or roles in various contexts

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

Head Attr Weights

0:0.02

1:0.01

2:0.09

3:0.07

4:0.08

5:0.04

6:0.03

7:0.34

8:0.04

9:0.04

10:0.10

11:0.09

Negative Logits

gor

-1.62

aciously

-1.59

 overload

-1.55

raq

-1.47

ouring

-1.45

geries

-1.44

 tricks

-1.44

 suggestion

-1.42

gery

-1.41

 consumes

-1.40

POSITIVE LOGITS

 Establishment

1.68

POS

1.63

ablishment

1.63

ilater

1.61

 bona

1.60

PATH

1.58

 Surviv

1.55

ADRA

1.53

 Cinem

1.51

 franchise

1.48

Activations Density 0.001%

phrases that indicate status or roles in various contexts

No Known Activations