INDEX

Explanations

specific terms associated with technical or mechanical operations and procedures

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

instances of repeated or emphasized phrases and words that indicate quantity or frequency

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.03

2:0.05

3:0.35

4:0.02

5:0.02

6:0.10

7:0.13

8:0.04

9:0.04

10:0.06

11:0.09

Negative Logits

��

-1.21

enegger

-1.14

�

-1.12

ouls

-1.11

etsk

-1.10

 Sanct

-1.10

ESA

-1.10

ibia

-1.10

 Lumpur

-1.09

UA

-1.08

POSITIVE LOGITS

itiveness

1.38

 loads

1.27

amaz

1.13

iencies

1.11

 soils

1.11

pack

1.08

 load

1.07

atten

1.06

uggish

1.06

aughter

1.06

Activations Density 0.007%

specific terms associated with technical or mechanical operations and procedures

instances of repeated or emphasized phrases and words that indicate quantity or frequency

No Comments

No Known Activations