INDEX

Explanations

gerunds and phrases related to challenges or difficulties faced by individuals

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.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

0:0.02

1:0.03

2:0.11

3:0.03

4:0.01

5:0.03

6:0.04

7:0.09

8:0.23

9:0.18

10:0.06

11:0.11

Negative Logits

ngth

-1.20

 respectively

-1.16

 trainer

-1.13

ials

-1.13

 plunged

-1.09

 awaits

-1.02

ーン

-1.00

letes

-0.98

 ensued

-0.98

 strives

-0.98

POSITIVE LOGITS

 Butt

1.41

addin

1.10

reating

1.05

tin

1.03

imating

1.03

TING

1.03

 Samoa

1.02

smoking

1.02

ال

1.01

 Guys

1.01

Activations Density 0.006%

gerunds and phrases related to challenges or difficulties faced by individuals

No Comments

No Known Activations