INDEX

Explanations

phrases related to forming and establishing frameworks or bases

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

1:0.03

2:0.13

3:0.03

4:0.01

5:0.04

6:0.05

7:0.06

8:0.14

9:0.30

10:0.07

11:0.06

Negative Logits

inventoryQuantity

-1.23

 VIDEOS

-1.19

 typo

-1.16

 scams

-1.14

 kindly

-1.13

 misunderstanding

-1.13

draft

-1.13

 forgot

-1.09

write

-1.09

Written

-1.09

POSITIVE LOGITS

cill

1.33

 Sacred

1.24

 Basil

1.24

 permanent

1.20

cone

1.19

manent

1.19

 vicinity

1.19

Ic

1.15

sonian

1.15

 mont

1.14

Activations Density 0.027%

phrases related to forming and establishing frameworks or bases

No Comments

No Known Activations