INDEX

Explanations

phrases related to relinquishing or giving up something

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

instances of giving up or relinquishing something

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

0:0.01

1:0.03

2:0.11

3:0.06

4:0.01

5:0.03

6:0.05

7:0.15

8:0.19

9:0.10

10:0.05

11:0.15

Negative Logits

inelli

-1.23

itect

-1.21

encer

-1.18

inel

-1.18

iti

-1.17

clair

-1.16

anu

-1.13

apeshifter

-1.13

imposed

-1.11

aghan

-1.11

POSITIVE LOGITS

netflix

1.17

 Beans

1.15

 steroids

1.11

 Names

1.05

 Cortex

1.04

 inheritance

1.02

 virginity

0.99

nces

0.98

Shares

0.98

 Medals

0.96

Activations Density 0.011%

phrases related to relinquishing or giving up something

instances of giving up or relinquishing something

No Comments

No Known Activations