INDEX

Explanations

mentions of influential figures, particularly Steve Jobs and Bill Gates, in the context of business and technology

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

0:0.05

1:0.03

2:0.07

3:0.03

4:0.04

5:0.08

6:0.19

7:0.24

8:0.04

9:0.04

10:0.09

11:0.05

Negative Logits

liga

-1.30

ás

-1.21

 deterrent

-1.18

icrobial

-1.13

venue

-1.13

eros

-1.05

idine

-1.04

rikes

-1.03

result

-1.02

 CARD

-1.02

POSITIVE LOGITS

 Reincarn

1.36

 reincarn

1.20

 Himself

1.18

 Revelations

1.18

 famously

1.18

 keynote

1.16

Untitled

1.12

 Creation

1.10

digy

1.09

keleton

1.09

Activations Density 0.007%

mentions of influential figures, particularly Steve Jobs and Bill Gates, in the context of business and technology

No Comments

No Known Activations