INDEX

Explanations

numerals beginning with '10'

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

references to age ranges and age-related concepts in individuals or contexts

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

2:0.04

3:0.33

4:0.02

5:0.02

6:0.05

7:0.12

8:0.04

9:0.14

10:0.05

11:0.07

Negative Logits

FML

-1.44

anchester

-1.43

atform

-1.26

odo

-1.23

fail

-1.17

eteenth

-1.17

latable

-1.15

olver

-1.13

 Guerrero

-1.09

istries

-1.08

POSITIVE LOGITS

1.39

inen

1.30

 Artemis

1.27

 WATCHED

1.27

 Painter

1.20

croft

1.19

nen

1.15

 corpus

1.14

seed

1.13

 Birds

1.12

Activations Density 0.007%

numerals beginning with '10'

references to age ranges and age-related concepts in individuals or contexts

No Comments

No Known Activations