INDEX

Explanations

phrases indicating difficulty or limitations

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

words that indicate limitations or restrictions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

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

Head Attr Weights

0:0.01

1:0.02

2:0.09

3:0.32

4:0.02

5:0.04

6:0.07

7:0.04

8:0.06

9:0.12

10:0.09

11:0.06

Negative Logits

 Notting

-1.07

heads

-1.03

 Gleaming

-1.02

aku

-0.92

 sidx

-0.91

hyde

-0.91

 Falls

-0.91

finding

-0.90

USL

-0.89

backer

-0.89

POSITIVE LOGITS

Brave

1.35

QL

1.30

CHAT

1.25

ILLE

1.23

efe

1.20

ovember

1.19

overe

1.16

��

1.14

redict

1.14

cffffcc

1.14

Activations Density 0.095%

phrases indicating difficulty or limitations

words that indicate limitations or restrictions

No Known Activations