INDEX

Explanations

names of people involved in news, stories, or social media posts

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

0:0.12

1:0.02

2:0.23

3:0.07

4:0.15

5:0.06

6:0.02

7:0.02

8:0.03

9:0.16

10:0.05

11:0.03

Negative Logits

etheless

-1.51

aucus

-1.32

▬

-1.32

ancies

-1.29

ディ

-1.26

ypes

-1.19

Particip

-1.19

theless

-1.18

Ire

-1.18

itures

-1.13

POSITIVE LOGITS

agher

1.33

��

1.23

ansk

1.18

bart

1.18

ansen

1.16

adr

1.15

angan

1.14

inger

1.10

RPC

1.08

hon

1.07

Activations Density 0.003%

names of people involved in news, stories, or social media posts

No Comments

No Known Activations