INDEX

Explanations

phrases related to age

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

1:0.03

2:0.18

3:0.13

4:0.11

5:0.07

6:0.04

7:0.02

8:0.08

9:0.10

10:0.07

11:0.03

Negative Logits

ッド

-1.57

Els

-1.57

yip

-1.56

ernels

-1.56

ickets

-1.54

xes

-1.51

wi

-1.51

ushima

-1.50

ュ

-1.49

odox

-1.48

POSITIVE LOGITS

 titled

1.48

 apology

1.45

 anniversary

1.44

 reunion

1.37

 apolog

1.35

 counselor

1.34

 Reilly

1.33

──

1.32

vet

1.31

 touring

1.30

Activations Density 0.008%

phrases related to age

No Comments

No Known Activations