INDEX

Explanations

words and phrases related to employment and work-related experiences

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

0:0.24

1:0.03

2:0.11

3:0.02

4:0.08

5:0.06

6:0.06

7:0.07

8:0.04

9:0.06

10:0.13

11:0.04

Negative Logits

RANT

-1.18

PDT

-1.10

 rendition

-1.05

 hysteria

-1.04

 Amazon

-1.04

 Billion

-1.00

 Snowden

-1.00

 verdict

-1.00

 Balloon

-0.99

 Mars

-0.98

POSITIVE LOGITS

 diligently

1.37

ework

1.36

assium

1.28

ateurs

1.26

enture

1.24

jobs

1.22

rower

1.22

├

1.21

 exha

1.20

 srfAttach

1.20

Activations Density 0.068%

words and phrases related to employment and work-related experiences

No Comments

No Known Activations