INDEX

Explanations

phrases indicating opposition or resistance to various actions or policies

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

1:0.05

2:0.09

3:0.04

4:0.02

5:0.06

6:0.05

7:0.05

8:0.14

9:0.07

10:0.08

11:0.27

Negative Logits

lia

-1.23

 condensed

-1.18

 optimized

-1.14

 exqu

-1.12

FINEST

-1.11

staking

-1.10

itone

-1.10

 manif

-1.09

 insulated

-1.06

 poked

-1.06

POSITIVE LOGITS

 anymore

1.39

cause

1.31

 altogether

1.17

erous

1.16

 Citation

1.16

 whatsoever

1.16

comments

1.16

 injust

1.15

 harms

1.15

 hurting

1.13

Activations Density 0.076%

phrases indicating opposition or resistance to various actions or policies

No Comments

No Known Activations