INDEX

Explanations

references to time-related phrases or contexts

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.04

1:0.03

2:0.03

3:0.06

4:0.05

5:0.05

6:0.05

7:0.06

8:0.02

9:0.12

10:0.03

11:0.40

Negative Logits

pots

-2.29

 targets

-2.27

itary

-2.19

 places

-2.15

issues

-2.11

spot

-2.11

 Places

-2.08

 outlets

-2.01

Policy

-2.00

 positions

-1.93

POSITIVE LOGITS

 chapter

2.65

 sequence

2.52

anza

2.42

 storyline

2.37

chapter

2.37

 narration

2.36

 semester

2.36

 subsequ

2.35

 playthrough

2.33

 rant

2.30

Activations Density 0.089%

references to time-related phrases or contexts

No Known Activations